update app.py && remove kolors/

app.py

@@ -78,12 +78,6 @@ from io import BytesIO
 from diffusers import StableDiffusionInpaintPipeline
 from huggingface_hub import hf_hub_download
 
-# from huggingface_hub import snapshot_download
-# from kolors.pipelines.pipeline_stable_diffusion_xl_chatglm_256_inpainting import StableDiffusionXLInpaintPipeline
-# from kolors.models.modeling_chatglm import ChatGLMModel
-# from kolors.models.tokenization_chatglm import ChatGLMTokenizer
-# from diffusers import AutoencoderKL, EulerDiscreteScheduler, UNet2DConditionModel
-
 from util_computer import computer_info
 
 # relate anything
@@ -334,24 +328,6 @@ def load_sd_model(device):
         #         torch_dtype=torch.float16,
         # )
         # sd_model = sd_model.to(device)
-
-        ckpt_dir = snapshot_download(repo_id="Kwai-Kolors/Kolors-Inpainting")
-        text_encoder = ChatGLMModel.from_pretrained(f'{ckpt_dir}/text_encoder',torch_dtype=torch.float16).half().to(device)
-        tokenizer = ChatGLMTokenizer.from_pretrained(f'{ckpt_dir}/text_encoder')
-        vae = AutoencoderKL.from_pretrained(f"{ckpt_dir}/vae", revision=None).half().to(device)
-        scheduler = EulerDiscreteScheduler.from_pretrained(f"{ckpt_dir}/scheduler")
-        unet = UNet2DConditionModel.from_pretrained(f"{ckpt_dir}/unet", revision=None).half().to(device)
-
-        sd_model = StableDiffusionXLInpaintPipeline(
-            vae=vae,
-            text_encoder=text_encoder,
-            tokenizer=tokenizer,
-            unet=unet,
-            scheduler=scheduler
-        )
-            
-        sd_model.to(device)
-        sd_model.enable_attention_slicing()
     '''
 
 def load_lama_cleaner_model(device):

kolors/models/configuration_chatglm.py

@@ -1,61 +0,0 @@
-from transformers import PretrainedConfig
-
-
-class ChatGLMConfig(PretrainedConfig):
-    model_type = "chatglm"
-    def __init__(
-        self,
-        num_layers=28,
-        padded_vocab_size=65024,
-        hidden_size=4096,
-        ffn_hidden_size=13696,
-        kv_channels=128,
-        num_attention_heads=32,
-        seq_length=2048,
-        hidden_dropout=0.0,
-        classifier_dropout=None,
-        attention_dropout=0.0,
-        layernorm_epsilon=1e-5,
-        rmsnorm=True,
-        apply_residual_connection_post_layernorm=False,
-        post_layer_norm=True,
-        add_bias_linear=False,
-        add_qkv_bias=False,
-        bias_dropout_fusion=True,
-        multi_query_attention=False,
-        multi_query_group_num=1,
-        apply_query_key_layer_scaling=True,
-        attention_softmax_in_fp32=True,
-        fp32_residual_connection=False,
-        quantization_bit=0,
-        pre_seq_len=None,
-        prefix_projection=False,
-        **kwargs
-    ):
-        self.num_layers = num_layers
-        self.vocab_size = padded_vocab_size
-        self.padded_vocab_size = padded_vocab_size
-        self.hidden_size = hidden_size
-        self.ffn_hidden_size = ffn_hidden_size
-        self.kv_channels = kv_channels
-        self.num_attention_heads = num_attention_heads
-        self.seq_length = seq_length
-        self.hidden_dropout = hidden_dropout
-        self.classifier_dropout = classifier_dropout
-        self.attention_dropout = attention_dropout
-        self.layernorm_epsilon = layernorm_epsilon
-        self.rmsnorm = rmsnorm
-        self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
-        self.post_layer_norm = post_layer_norm
-        self.add_bias_linear = add_bias_linear
-        self.add_qkv_bias = add_qkv_bias
-        self.bias_dropout_fusion = bias_dropout_fusion
-        self.multi_query_attention = multi_query_attention
-        self.multi_query_group_num = multi_query_group_num
-        self.apply_query_key_layer_scaling = apply_query_key_layer_scaling
-        self.attention_softmax_in_fp32 = attention_softmax_in_fp32
-        self.fp32_residual_connection = fp32_residual_connection
-        self.quantization_bit = quantization_bit
-        self.pre_seq_len = pre_seq_len
-        self.prefix_projection = prefix_projection
-        super().__init__(**kwargs)

kolors/models/controlnet.py

@@ -1,887 +0,0 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional, Tuple, Union
-
-import torch
-from torch import nn
-from torch.nn import functional as F
-
-from diffusers.configuration_utils import ConfigMixin, register_to_config
-from diffusers.loaders.single_file_model import FromOriginalModelMixin
-from diffusers.utils import BaseOutput, logging
-from diffusers.models.attention_processor import (
-    ADDED_KV_ATTENTION_PROCESSORS,
-    CROSS_ATTENTION_PROCESSORS,
-    AttentionProcessor,
-    AttnAddedKVProcessor,
-    AttnProcessor,
-)
-from diffusers.models.embeddings import TextImageProjection, TextImageTimeEmbedding, TextTimeEmbedding, TimestepEmbedding, Timesteps
-from diffusers.models.modeling_utils import ModelMixin
-
-try:
-    from diffusers.unets.unet_2d_blocks import (
-        CrossAttnDownBlock2D,
-        DownBlock2D,
-        UNetMidBlock2D,
-        UNetMidBlock2DCrossAttn,
-        get_down_block,
-    )
-    from diffusers.unets.unet_2d_condition import UNet2DConditionModel
-except:
-    from diffusers.models.unets.unet_2d_blocks import (
-        CrossAttnDownBlock2D,
-        DownBlock2D,
-        UNetMidBlock2D,
-        UNetMidBlock2DCrossAttn,
-        get_down_block,
-    )
-    from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
-
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-@dataclass
-class ControlNetOutput(BaseOutput):
-    """
-    The output of [`ControlNetModel`].
-
-    Args:
-        down_block_res_samples (`tuple[torch.Tensor]`):
-            A tuple of downsample activations at different resolutions for each downsampling block. Each tensor should
-            be of shape `(batch_size, channel * resolution, height //resolution, width // resolution)`. Output can be
-            used to condition the original UNet's downsampling activations.
-        mid_down_block_re_sample (`torch.Tensor`):
-            The activation of the middle block (the lowest sample resolution). Each tensor should be of shape
-            `(batch_size, channel * lowest_resolution, height // lowest_resolution, width // lowest_resolution)`.
-            Output can be used to condition the original UNet's middle block activation.
-    """
-
-    down_block_res_samples: Tuple[torch.Tensor]
-    mid_block_res_sample: torch.Tensor
-
-
-class ControlNetConditioningEmbedding(nn.Module):
-    """
-    Quoting from https://arxiv.org/abs/2302.05543: "Stable Diffusion uses a pre-processing method similar to VQ-GAN
-    [11] to convert the entire dataset of 512 × 512 images into smaller 64 × 64 “latent images” for stabilized
-    training. This requires ControlNets to convert image-based conditions to 64 × 64 feature space to match the
-    convolution size. We use a tiny network E(·) of four convolution layers with 4 × 4 kernels and 2 × 2 strides
-    (activated by ReLU, channels are 16, 32, 64, 128, initialized with Gaussian weights, trained jointly with the full
-    model) to encode image-space conditions ... into feature maps ..."
-    """
-
-    def __init__(
-        self,
-        conditioning_embedding_channels: int,
-        conditioning_channels: int = 3,
-        block_out_channels: Tuple[int, ...] = (16, 32, 96, 256),
-    ):
-        super().__init__()
-
-        self.conv_in = nn.Conv2d(conditioning_channels, block_out_channels[0], kernel_size=3, padding=1)
-
-        self.blocks = nn.ModuleList([])
-
-        for i in range(len(block_out_channels) - 1):
-            channel_in = block_out_channels[i]
-            channel_out = block_out_channels[i + 1]
-            self.blocks.append(nn.Conv2d(channel_in, channel_in, kernel_size=3, padding=1))
-            self.blocks.append(nn.Conv2d(channel_in, channel_out, kernel_size=3, padding=1, stride=2))
-
-        self.conv_out = zero_module(
-            nn.Conv2d(block_out_channels[-1], conditioning_embedding_channels, kernel_size=3, padding=1)
-        )
-
-    def forward(self, conditioning):
-        embedding = self.conv_in(conditioning)
-        embedding = F.silu(embedding)
-
-        for block in self.blocks:
-            embedding = block(embedding)
-            embedding = F.silu(embedding)
-
-        embedding = self.conv_out(embedding)
-
-        return embedding
-
-
-class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalModelMixin):
-    """
-    A ControlNet model.
-
-    Args:
-        in_channels (`int`, defaults to 4):
-            The number of channels in the input sample.
-        flip_sin_to_cos (`bool`, defaults to `True`):
-            Whether to flip the sin to cos in the time embedding.
-        freq_shift (`int`, defaults to 0):
-            The frequency shift to apply to the time embedding.
-        down_block_types (`tuple[str]`, defaults to `("CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "DownBlock2D")`):
-            The tuple of downsample blocks to use.
-        only_cross_attention (`Union[bool, Tuple[bool]]`, defaults to `False`):
-        block_out_channels (`tuple[int]`, defaults to `(320, 640, 1280, 1280)`):
-            The tuple of output channels for each block.
-        layers_per_block (`int`, defaults to 2):
-            The number of layers per block.
-        downsample_padding (`int`, defaults to 1):
-            The padding to use for the downsampling convolution.
-        mid_block_scale_factor (`float`, defaults to 1):
-            The scale factor to use for the mid block.
-        act_fn (`str`, defaults to "silu"):
-            The activation function to use.
-        norm_num_groups (`int`, *optional*, defaults to 32):
-            The number of groups to use for the normalization. If None, normalization and activation layers is skipped
-            in post-processing.
-        norm_eps (`float`, defaults to 1e-5):
-            The epsilon to use for the normalization.
-        cross_attention_dim (`int`, defaults to 1280):
-            The dimension of the cross attention features.
-        transformer_layers_per_block (`int` or `Tuple[int]`, *optional*, defaults to 1):
-            The number of transformer blocks of type [`~models.attention.BasicTransformerBlock`]. Only relevant for
-            [`~models.unet_2d_blocks.CrossAttnDownBlock2D`], [`~models.unet_2d_blocks.CrossAttnUpBlock2D`],
-            [`~models.unet_2d_blocks.UNetMidBlock2DCrossAttn`].
-        encoder_hid_dim (`int`, *optional*, defaults to None):
-            If `encoder_hid_dim_type` is defined, `encoder_hidden_states` will be projected from `encoder_hid_dim`
-            dimension to `cross_attention_dim`.
-        encoder_hid_dim_type (`str`, *optional*, defaults to `None`):
-            If given, the `encoder_hidden_states` and potentially other embeddings are down-projected to text
-            embeddings of dimension `cross_attention` according to `encoder_hid_dim_type`.
-        attention_head_dim (`Union[int, Tuple[int]]`, defaults to 8):
-            The dimension of the attention heads.
-        use_linear_projection (`bool`, defaults to `False`):
-        class_embed_type (`str`, *optional*, defaults to `None`):
-            The type of class embedding to use which is ultimately summed with the time embeddings. Choose from None,
-            `"timestep"`, `"identity"`, `"projection"`, or `"simple_projection"`.
-        addition_embed_type (`str`, *optional*, defaults to `None`):
-            Configures an optional embedding which will be summed with the time embeddings. Choose from `None` or
-            "text". "text" will use the `TextTimeEmbedding` layer.
-        num_class_embeds (`int`, *optional*, defaults to 0):
-            Input dimension of the learnable embedding matrix to be projected to `time_embed_dim`, when performing
-            class conditioning with `class_embed_type` equal to `None`.
-        upcast_attention (`bool`, defaults to `False`):
-        resnet_time_scale_shift (`str`, defaults to `"default"`):
-            Time scale shift config for ResNet blocks (see `ResnetBlock2D`). Choose from `default` or `scale_shift`.
-        projection_class_embeddings_input_dim (`int`, *optional*, defaults to `None`):
-            The dimension of the `class_labels` input when `class_embed_type="projection"`. Required when
-            `class_embed_type="projection"`.
-        controlnet_conditioning_channel_order (`str`, defaults to `"rgb"`):
-            The channel order of conditional image. Will convert to `rgb` if it's `bgr`.
-        conditioning_embedding_out_channels (`tuple[int]`, *optional*, defaults to `(16, 32, 96, 256)`):
-            The tuple of output channel for each block in the `conditioning_embedding` layer.
-        global_pool_conditions (`bool`, defaults to `False`):
-            TODO(Patrick) - unused parameter.
-        addition_embed_type_num_heads (`int`, defaults to 64):
-            The number of heads to use for the `TextTimeEmbedding` layer.
-    """
-
-    _supports_gradient_checkpointing = True
-
-    @register_to_config
-    def __init__(
-        self,
-        in_channels: int = 4,
-        conditioning_channels: int = 3,
-        flip_sin_to_cos: bool = True,
-        freq_shift: int = 0,
-        down_block_types: Tuple[str, ...] = (
-            "CrossAttnDownBlock2D",
-            "CrossAttnDownBlock2D",
-            "CrossAttnDownBlock2D",
-            "DownBlock2D",
-        ),
-        mid_block_type: Optional[str] = "UNetMidBlock2DCrossAttn",
-        only_cross_attention: Union[bool, Tuple[bool]] = False,
-        block_out_channels: Tuple[int, ...] = (320, 640, 1280, 1280),
-        layers_per_block: int = 2,
-        downsample_padding: int = 1,
-        mid_block_scale_factor: float = 1,
-        act_fn: str = "silu",
-        norm_num_groups: Optional[int] = 32,
-        norm_eps: float = 1e-5,
-        cross_attention_dim: int = 1280,
-        transformer_layers_per_block: Union[int, Tuple[int, ...]] = 1,
-        encoder_hid_dim: Optional[int] = None,
-        encoder_hid_dim_type: Optional[str] = None,
-        attention_head_dim: Union[int, Tuple[int, ...]] = 8,
-        num_attention_heads: Optional[Union[int, Tuple[int, ...]]] = None,
-        use_linear_projection: bool = False,
-        class_embed_type: Optional[str] = None,
-        addition_embed_type: Optional[str] = None,
-        addition_time_embed_dim: Optional[int] = None,
-        num_class_embeds: Optional[int] = None,
-        upcast_attention: bool = False,
-        resnet_time_scale_shift: str = "default",
-        projection_class_embeddings_input_dim: Optional[int] = None,
-        controlnet_conditioning_channel_order: str = "rgb",
-        conditioning_embedding_out_channels: Optional[Tuple[int, ...]] = (16, 32, 96, 256),
-        global_pool_conditions: bool = False,
-        addition_embed_type_num_heads: int = 64,
-    ):
-        super().__init__()
-
-        # If `num_attention_heads` is not defined (which is the case for most models)
-        # it will default to `attention_head_dim`. This looks weird upon first reading it and it is.
-        # The reason for this behavior is to correct for incorrectly named variables that were introduced
-        # when this library was created. The incorrect naming was only discovered much later in https://github.com/huggingface/diffusers/issues/2011#issuecomment-1547958131
-        # Changing `attention_head_dim` to `num_attention_heads` for 40,000+ configurations is too backwards breaking
-        # which is why we correct for the naming here.
-        num_attention_heads = num_attention_heads or attention_head_dim
-
-        # Check inputs
-        if len(block_out_channels) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `block_out_channels` as `down_block_types`. `block_out_channels`: {block_out_channels}. `down_block_types`: {down_block_types}."
-            )
-
-        if not isinstance(only_cross_attention, bool) and len(only_cross_attention) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `only_cross_attention` as `down_block_types`. `only_cross_attention`: {only_cross_attention}. `down_block_types`: {down_block_types}."
-            )
-
-        if not isinstance(num_attention_heads, int) and len(num_attention_heads) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `num_attention_heads` as `down_block_types`. `num_attention_heads`: {num_attention_heads}. `down_block_types`: {down_block_types}."
-            )
-
-        if isinstance(transformer_layers_per_block, int):
-            transformer_layers_per_block = [transformer_layers_per_block] * len(down_block_types)
-
-        # input
-        conv_in_kernel = 3
-        conv_in_padding = (conv_in_kernel - 1) // 2
-        self.conv_in = nn.Conv2d(
-            in_channels, block_out_channels[0], kernel_size=conv_in_kernel, padding=conv_in_padding
-        )
-
-        # time
-        time_embed_dim = block_out_channels[0] * 4
-        self.time_proj = Timesteps(block_out_channels[0], flip_sin_to_cos, freq_shift)
-        timestep_input_dim = block_out_channels[0]
-        self.time_embedding = TimestepEmbedding(
-            timestep_input_dim,
-            time_embed_dim,
-            act_fn=act_fn,
-        )
-
-        if encoder_hid_dim_type is None and encoder_hid_dim is not None:
-            encoder_hid_dim_type = "text_proj"
-            self.register_to_config(encoder_hid_dim_type=encoder_hid_dim_type)
-            logger.info("encoder_hid_dim_type defaults to 'text_proj' as `encoder_hid_dim` is defined.")
-
-        if encoder_hid_dim is None and encoder_hid_dim_type is not None:
-            raise ValueError(
-                f"`encoder_hid_dim` has to be defined when `encoder_hid_dim_type` is set to {encoder_hid_dim_type}."
-            )
-
-        if encoder_hid_dim_type == "text_proj":
-            self.encoder_hid_proj = nn.Linear(encoder_hid_dim, cross_attention_dim)
-        elif encoder_hid_dim_type == "text_image_proj":
-            # image_embed_dim DOESN'T have to be `cross_attention_dim`. To not clutter the __init__ too much
-            # they are set to `cross_attention_dim` here as this is exactly the required dimension for the currently only use
-            # case when `addition_embed_type == "text_image_proj"` (Kandinsky 2.1)`
-            self.encoder_hid_proj = TextImageProjection(
-                text_embed_dim=encoder_hid_dim,
-                image_embed_dim=cross_attention_dim,
-                cross_attention_dim=cross_attention_dim,
-            )
-
-        elif encoder_hid_dim_type is not None:
-            raise ValueError(
-                f"encoder_hid_dim_type: {encoder_hid_dim_type} must be None, 'text_proj' or 'text_image_proj'."
-            )
-        else:
-            self.encoder_hid_proj = None
-
-        # class embedding
-        if class_embed_type is None and num_class_embeds is not None:
-            self.class_embedding = nn.Embedding(num_class_embeds, time_embed_dim)
-        elif class_embed_type == "timestep":
-            self.class_embedding = TimestepEmbedding(timestep_input_dim, time_embed_dim)
-        elif class_embed_type == "identity":
-            self.class_embedding = nn.Identity(time_embed_dim, time_embed_dim)
-        elif class_embed_type == "projection":
-            if projection_class_embeddings_input_dim is None:
-                raise ValueError(
-                    "`class_embed_type`: 'projection' requires `projection_class_embeddings_input_dim` be set"
-                )
-            # The projection `class_embed_type` is the same as the timestep `class_embed_type` except
-            # 1. the `class_labels` inputs are not first converted to sinusoidal embeddings
-            # 2. it projects from an arbitrary input dimension.
-            #
-            # Note that `TimestepEmbedding` is quite general, being mainly linear layers and activations.
-            # When used for embedding actual timesteps, the timesteps are first converted to sinusoidal embeddings.
-            # As a result, `TimestepEmbedding` can be passed arbitrary vectors.
-            self.class_embedding = TimestepEmbedding(projection_class_embeddings_input_dim, time_embed_dim)
-        else:
-            self.class_embedding = None
-
-        if addition_embed_type == "text":
-            if encoder_hid_dim is not None:
-                text_time_embedding_from_dim = encoder_hid_dim
-            else:
-                text_time_embedding_from_dim = cross_attention_dim
-
-            self.add_embedding = TextTimeEmbedding(
-                text_time_embedding_from_dim, time_embed_dim, num_heads=addition_embed_type_num_heads
-            )
-        elif addition_embed_type == "text_image":
-            # text_embed_dim and image_embed_dim DON'T have to be `cross_attention_dim`. To not clutter the __init__ too much
-            # they are set to `cross_attention_dim` here as this is exactly the required dimension for the currently only use
-            # case when `addition_embed_type == "text_image"` (Kandinsky 2.1)`
-            self.add_embedding = TextImageTimeEmbedding(
-                text_embed_dim=cross_attention_dim, image_embed_dim=cross_attention_dim, time_embed_dim=time_embed_dim
-            )
-        elif addition_embed_type == "text_time":
-            self.add_time_proj = Timesteps(addition_time_embed_dim, flip_sin_to_cos, freq_shift)
-            self.add_embedding = TimestepEmbedding(projection_class_embeddings_input_dim, time_embed_dim)
-
-        elif addition_embed_type is not None:
-            raise ValueError(f"addition_embed_type: {addition_embed_type} must be None, 'text' or 'text_image'.")
-
-        # control net conditioning embedding
-        self.controlnet_cond_embedding = ControlNetConditioningEmbedding(
-            conditioning_embedding_channels=block_out_channels[0],
-            block_out_channels=conditioning_embedding_out_channels,
-            conditioning_channels=conditioning_channels,
-        )
-
-        self.down_blocks = nn.ModuleList([])
-        self.controlnet_down_blocks = nn.ModuleList([])
-
-        if isinstance(only_cross_attention, bool):
-            only_cross_attention = [only_cross_attention] * len(down_block_types)
-
-        if isinstance(attention_head_dim, int):
-            attention_head_dim = (attention_head_dim,) * len(down_block_types)
-
-        if isinstance(num_attention_heads, int):
-            num_attention_heads = (num_attention_heads,) * len(down_block_types)
-
-        # down
-        output_channel = block_out_channels[0]
-
-        controlnet_block = nn.Conv2d(output_channel, output_channel, kernel_size=1)
-        controlnet_block = zero_module(controlnet_block)
-        self.controlnet_down_blocks.append(controlnet_block)
-
-        for i, down_block_type in enumerate(down_block_types):
-            input_channel = output_channel
-            output_channel = block_out_channels[i]
-            is_final_block = i == len(block_out_channels) - 1
-
-            down_block = get_down_block(
-                down_block_type,
-                num_layers=layers_per_block,
-                transformer_layers_per_block=transformer_layers_per_block[i],
-                in_channels=input_channel,
-                out_channels=output_channel,
-                temb_channels=time_embed_dim,
-                add_downsample=not is_final_block,
-                resnet_eps=norm_eps,
-                resnet_act_fn=act_fn,
-                resnet_groups=norm_num_groups,
-                cross_attention_dim=cross_attention_dim,
-                num_attention_heads=num_attention_heads[i],
-                attention_head_dim=attention_head_dim[i] if attention_head_dim[i] is not None else output_channel,
-                downsample_padding=downsample_padding,
-                use_linear_projection=use_linear_projection,
-                only_cross_attention=only_cross_attention[i],
-                upcast_attention=upcast_attention,
-                resnet_time_scale_shift=resnet_time_scale_shift,
-            )
-            self.down_blocks.append(down_block)
-
-            for _ in range(layers_per_block):
-                controlnet_block = nn.Conv2d(output_channel, output_channel, kernel_size=1)
-                controlnet_block = zero_module(controlnet_block)
-                self.controlnet_down_blocks.append(controlnet_block)
-
-            if not is_final_block:
-                controlnet_block = nn.Conv2d(output_channel, output_channel, kernel_size=1)
-                controlnet_block = zero_module(controlnet_block)
-                self.controlnet_down_blocks.append(controlnet_block)
-
-        # mid
-        mid_block_channel = block_out_channels[-1]
-
-        controlnet_block = nn.Conv2d(mid_block_channel, mid_block_channel, kernel_size=1)
-        controlnet_block = zero_module(controlnet_block)
-        self.controlnet_mid_block = controlnet_block
-
-        if mid_block_type == "UNetMidBlock2DCrossAttn":
-            self.mid_block = UNetMidBlock2DCrossAttn(
-                transformer_layers_per_block=transformer_layers_per_block[-1],
-                in_channels=mid_block_channel,
-                temb_channels=time_embed_dim,
-                resnet_eps=norm_eps,
-                resnet_act_fn=act_fn,
-                output_scale_factor=mid_block_scale_factor,
-                resnet_time_scale_shift=resnet_time_scale_shift,
-                cross_attention_dim=cross_attention_dim,
-                num_attention_heads=num_attention_heads[-1],
-                resnet_groups=norm_num_groups,
-                use_linear_projection=use_linear_projection,
-                upcast_attention=upcast_attention,
-            )
-        elif mid_block_type == "UNetMidBlock2D":
-            self.mid_block = UNetMidBlock2D(
-                in_channels=block_out_channels[-1],
-                temb_channels=time_embed_dim,
-                num_layers=0,
-                resnet_eps=norm_eps,
-                resnet_act_fn=act_fn,
-                output_scale_factor=mid_block_scale_factor,
-                resnet_groups=norm_num_groups,
-                resnet_time_scale_shift=resnet_time_scale_shift,
-                add_attention=False,
-            )
-        else:
-            raise ValueError(f"unknown mid_block_type : {mid_block_type}")
-
-    @classmethod
-    def from_unet(
-        cls,
-        unet: UNet2DConditionModel,
-        controlnet_conditioning_channel_order: str = "rgb",
-        conditioning_embedding_out_channels: Optional[Tuple[int, ...]] = (16, 32, 96, 256),
-        load_weights_from_unet: bool = True,
-        conditioning_channels: int = 3,
-    ):
-        r"""
-        Instantiate a [`ControlNetModel`] from [`UNet2DConditionModel`].
-
-        Parameters:
-            unet (`UNet2DConditionModel`):
-                The UNet model weights to copy to the [`ControlNetModel`]. All configuration options are also copied
-                where applicable.
-        """
-        transformer_layers_per_block = (
-            unet.config.transformer_layers_per_block if "transformer_layers_per_block" in unet.config else 1
-        )
-        encoder_hid_dim = unet.config.encoder_hid_dim if "encoder_hid_dim" in unet.config else None
-        encoder_hid_dim_type = unet.config.encoder_hid_dim_type if "encoder_hid_dim_type" in unet.config else None
-        addition_embed_type = unet.config.addition_embed_type if "addition_embed_type" in unet.config else None
-        addition_time_embed_dim = (
-            unet.config.addition_time_embed_dim if "addition_time_embed_dim" in unet.config else None
-        )
-
-        controlnet = cls(
-            encoder_hid_dim=encoder_hid_dim,
-            encoder_hid_dim_type=encoder_hid_dim_type,
-            addition_embed_type=addition_embed_type,
-            addition_time_embed_dim=addition_time_embed_dim,
-            transformer_layers_per_block=transformer_layers_per_block,
-            in_channels=unet.config.in_channels,
-            flip_sin_to_cos=unet.config.flip_sin_to_cos,
-            freq_shift=unet.config.freq_shift,
-            down_block_types=unet.config.down_block_types,
-            only_cross_attention=unet.config.only_cross_attention,
-            block_out_channels=unet.config.block_out_channels,
-            layers_per_block=unet.config.layers_per_block,
-            downsample_padding=unet.config.downsample_padding,
-            mid_block_scale_factor=unet.config.mid_block_scale_factor,
-            act_fn=unet.config.act_fn,
-            norm_num_groups=unet.config.norm_num_groups,
-            norm_eps=unet.config.norm_eps,
-            cross_attention_dim=unet.config.cross_attention_dim,
-            attention_head_dim=unet.config.attention_head_dim,
-            num_attention_heads=unet.config.num_attention_heads,
-            use_linear_projection=unet.config.use_linear_projection,
-            class_embed_type=unet.config.class_embed_type,
-            num_class_embeds=unet.config.num_class_embeds,
-            upcast_attention=unet.config.upcast_attention,
-            resnet_time_scale_shift=unet.config.resnet_time_scale_shift,
-            projection_class_embeddings_input_dim=unet.config.projection_class_embeddings_input_dim,
-            mid_block_type=unet.config.mid_block_type,
-            controlnet_conditioning_channel_order=controlnet_conditioning_channel_order,
-            conditioning_embedding_out_channels=conditioning_embedding_out_channels,
-            conditioning_channels=conditioning_channels,
-        )
-
-        if load_weights_from_unet:
-            controlnet.conv_in.load_state_dict(unet.conv_in.state_dict())
-            controlnet.time_proj.load_state_dict(unet.time_proj.state_dict())
-            controlnet.time_embedding.load_state_dict(unet.time_embedding.state_dict())
-
-            if controlnet.class_embedding:
-                controlnet.class_embedding.load_state_dict(unet.class_embedding.state_dict())
-
-            if hasattr(controlnet, "add_embedding"):
-                controlnet.add_embedding.load_state_dict(unet.add_embedding.state_dict())
-
-            controlnet.down_blocks.load_state_dict(unet.down_blocks.state_dict())
-            controlnet.mid_block.load_state_dict(unet.mid_block.state_dict())
-
-        return controlnet
-
-    @property
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.attn_processors
-    def attn_processors(self) -> Dict[str, AttentionProcessor]:
-        r"""
-        Returns:
-            `dict` of attention processors: A dictionary containing all attention processors used in the model with
-            indexed by its weight name.
-        """
-        # set recursively
-        processors = {}
-
-        def fn_recursive_add_processors(name: str, module: torch.nn.Module, processors: Dict[str, AttentionProcessor]):
-            if hasattr(module, "get_processor"):
-                processors[f"{name}.processor"] = module.get_processor()
-
-            for sub_name, child in module.named_children():
-                fn_recursive_add_processors(f"{name}.{sub_name}", child, processors)
-
-            return processors
-
-        for name, module in self.named_children():
-            fn_recursive_add_processors(name, module, processors)
-
-        return processors
-
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.set_attn_processor
-    def set_attn_processor(self, processor: Union[AttentionProcessor, Dict[str, AttentionProcessor]]):
-        r"""
-        Sets the attention processor to use to compute attention.
-
-        Parameters:
-            processor (`dict` of `AttentionProcessor` or only `AttentionProcessor`):
-                The instantiated processor class or a dictionary of processor classes that will be set as the processor
-                for **all** `Attention` layers.
-
-                If `processor` is a dict, the key needs to define the path to the corresponding cross attention
-                processor. This is strongly recommended when setting trainable attention processors.
-
-        """
-        count = len(self.attn_processors.keys())
-
-        if isinstance(processor, dict) and len(processor) != count:
-            raise ValueError(
-                f"A dict of processors was passed, but the number of processors {len(processor)} does not match the"
-                f" number of attention layers: {count}. Please make sure to pass {count} processor classes."
-            )
-
-        def fn_recursive_attn_processor(name: str, module: torch.nn.Module, processor):
-            if hasattr(module, "set_processor"):
-                if not isinstance(processor, dict):
-                    module.set_processor(processor)
-                else:
-                    module.set_processor(processor.pop(f"{name}.processor"))
-
-            for sub_name, child in module.named_children():
-                fn_recursive_attn_processor(f"{name}.{sub_name}", child, processor)
-
-        for name, module in self.named_children():
-            fn_recursive_attn_processor(name, module, processor)
-
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.set_default_attn_processor
-    def set_default_attn_processor(self):
-        """
-        Disables custom attention processors and sets the default attention implementation.
-        """
-        if all(proc.__class__ in ADDED_KV_ATTENTION_PROCESSORS for proc in self.attn_processors.values()):
-            processor = AttnAddedKVProcessor()
-        elif all(proc.__class__ in CROSS_ATTENTION_PROCESSORS for proc in self.attn_processors.values()):
-            processor = AttnProcessor()
-        else:
-            raise ValueError(
-                f"Cannot call `set_default_attn_processor` when attention processors are of type {next(iter(self.attn_processors.values()))}"
-            )
-
-        self.set_attn_processor(processor)
-
-    # Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.set_attention_slice
-    def set_attention_slice(self, slice_size: Union[str, int, List[int]]) -> None:
-        r"""
-        Enable sliced attention computation.
-
-        When this option is enabled, the attention module splits the input tensor in slices to compute attention in
-        several steps. This is useful for saving some memory in exchange for a small decrease in speed.
-
-        Args:
-            slice_size (`str` or `int` or `list(int)`, *optional*, defaults to `"auto"`):
-                When `"auto"`, input to the attention heads is halved, so attention is computed in two steps. If
-                `"max"`, maximum amount of memory is saved by running only one slice at a time. If a number is
-                provided, uses as many slices as `attention_head_dim // slice_size`. In this case, `attention_head_dim`
-                must be a multiple of `slice_size`.
-        """
-        sliceable_head_dims = []
-
-        def fn_recursive_retrieve_sliceable_dims(module: torch.nn.Module):
-            if hasattr(module, "set_attention_slice"):
-                sliceable_head_dims.append(module.sliceable_head_dim)
-
-            for child in module.children():
-                fn_recursive_retrieve_sliceable_dims(child)
-
-        # retrieve number of attention layers
-        for module in self.children():
-            fn_recursive_retrieve_sliceable_dims(module)
-
-        num_sliceable_layers = len(sliceable_head_dims)
-
-        if slice_size == "auto":
-            # half the attention head size is usually a good trade-off between
-            # speed and memory
-            slice_size = [dim // 2 for dim in sliceable_head_dims]
-        elif slice_size == "max":
-            # make smallest slice possible
-            slice_size = num_sliceable_layers * [1]
-
-        slice_size = num_sliceable_layers * [slice_size] if not isinstance(slice_size, list) else slice_size
-
-        if len(slice_size) != len(sliceable_head_dims):
-            raise ValueError(
-                f"You have provided {len(slice_size)}, but {self.config} has {len(sliceable_head_dims)} different"
-                f" attention layers. Make sure to match `len(slice_size)` to be {len(sliceable_head_dims)}."
-            )
-
-        for i in range(len(slice_size)):
-            size = slice_size[i]
-            dim = sliceable_head_dims[i]
-            if size is not None and size > dim:
-                raise ValueError(f"size {size} has to be smaller or equal to {dim}.")
-
-        # Recursively walk through all the children.
-        # Any children which exposes the set_attention_slice method
-        # gets the message
-        def fn_recursive_set_attention_slice(module: torch.nn.Module, slice_size: List[int]):
-            if hasattr(module, "set_attention_slice"):
-                module.set_attention_slice(slice_size.pop())
-
-            for child in module.children():
-                fn_recursive_set_attention_slice(child, slice_size)
-
-        reversed_slice_size = list(reversed(slice_size))
-        for module in self.children():
-            fn_recursive_set_attention_slice(module, reversed_slice_size)
-
-    def _set_gradient_checkpointing(self, module, value: bool = False) -> None:
-        if isinstance(module, (CrossAttnDownBlock2D, DownBlock2D)):
-            module.gradient_checkpointing = value
-
-    def forward(
-        self,
-        sample: torch.Tensor,
-        timestep: Union[torch.Tensor, float, int],
-        encoder_hidden_states: torch.Tensor,
-        controlnet_cond: torch.Tensor,
-        conditioning_scale: float = 1.0,
-        class_labels: Optional[torch.Tensor] = None,
-        timestep_cond: Optional[torch.Tensor] = None,
-        attention_mask: Optional[torch.Tensor] = None,
-        added_cond_kwargs: Optional[Dict[str, torch.Tensor]] = None,
-        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-        guess_mode: bool = False,
-        return_dict: bool = True,
-    ) -> Union[ControlNetOutput, Tuple[Tuple[torch.Tensor, ...], torch.Tensor]]:
-        """
-        The [`ControlNetModel`] forward method.
-
-        Args:
-            sample (`torch.Tensor`):
-                The noisy input tensor.
-            timestep (`Union[torch.Tensor, float, int]`):
-                The number of timesteps to denoise an input.
-            encoder_hidden_states (`torch.Tensor`):
-                The encoder hidden states.
-            controlnet_cond (`torch.Tensor`):
-                The conditional input tensor of shape `(batch_size, sequence_length, hidden_size)`.
-            conditioning_scale (`float`, defaults to `1.0`):
-                The scale factor for ControlNet outputs.
-            class_labels (`torch.Tensor`, *optional*, defaults to `None`):
-                Optional class labels for conditioning. Their embeddings will be summed with the timestep embeddings.
-            timestep_cond (`torch.Tensor`, *optional*, defaults to `None`):
-                Additional conditional embeddings for timestep. If provided, the embeddings will be summed with the
-                timestep_embedding passed through the `self.time_embedding` layer to obtain the final timestep
-                embeddings.
-            attention_mask (`torch.Tensor`, *optional*, defaults to `None`):
-                An attention mask of shape `(batch, key_tokens)` is applied to `encoder_hidden_states`. If `1` the mask
-                is kept, otherwise if `0` it is discarded. Mask will be converted into a bias, which adds large
-                negative values to the attention scores corresponding to "discard" tokens.
-            added_cond_kwargs (`dict`):
-                Additional conditions for the Stable Diffusion XL UNet.
-            cross_attention_kwargs (`dict[str]`, *optional*, defaults to `None`):
-                A kwargs dictionary that if specified is passed along to the `AttnProcessor`.
-            guess_mode (`bool`, defaults to `False`):
-                In this mode, the ControlNet encoder tries its best to recognize the input content of the input even if
-                you remove all prompts. A `guidance_scale` between 3.0 and 5.0 is recommended.
-            return_dict (`bool`, defaults to `True`):
-                Whether or not to return a [`~models.controlnet.ControlNetOutput`] instead of a plain tuple.
-
-        Returns:
-            [`~models.controlnet.ControlNetOutput`] **or** `tuple`:
-                If `return_dict` is `True`, a [`~models.controlnet.ControlNetOutput`] is returned, otherwise a tuple is
-                returned where the first element is the sample tensor.
-        """
-        # check channel order
-        channel_order = self.config.controlnet_conditioning_channel_order
-
-        if channel_order == "rgb":
-            # in rgb order by default
-            ...
-        elif channel_order == "bgr":
-            controlnet_cond = torch.flip(controlnet_cond, dims=[1])
-        else:
-            raise ValueError(f"unknown `controlnet_conditioning_channel_order`: {channel_order}")
-
-        # prepare attention_mask
-        if attention_mask is not None:
-            attention_mask = (1 - attention_mask.to(sample.dtype)) * -10000.0
-            attention_mask = attention_mask.unsqueeze(1)
-
-        #Todo 
-        if self.encoder_hid_proj is not None and self.config.encoder_hid_dim_type == "text_proj":
-            encoder_hidden_states = self.encoder_hid_proj(encoder_hidden_states)
-
-        # 1. time
-        timesteps = timestep
-        if not torch.is_tensor(timesteps):
-            # TODO: this requires sync between CPU and GPU. So try to pass timesteps as tensors if you can
-            # This would be a good case for the `match` statement (Python 3.10+)
-            is_mps = sample.device.type == "mps"
-            if isinstance(timestep, float):
-                dtype = torch.float32 if is_mps else torch.float64
-            else:
-                dtype = torch.int32 if is_mps else torch.int64
-            timesteps = torch.tensor([timesteps], dtype=dtype, device=sample.device)
-        elif len(timesteps.shape) == 0:
-            timesteps = timesteps[None].to(sample.device)
-
-        # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
-        timesteps = timesteps.expand(sample.shape[0])
-
-        t_emb = self.time_proj(timesteps)
-
-        # timesteps does not contain any weights and will always return f32 tensors
-        # but time_embedding might actually be running in fp16. so we need to cast here.
-        # there might be better ways to encapsulate this.
-        t_emb = t_emb.to(dtype=sample.dtype)
-
-        emb = self.time_embedding(t_emb, timestep_cond)
-        aug_emb = None
-
-        if self.class_embedding is not None:
-            if class_labels is None:
-                raise ValueError("class_labels should be provided when num_class_embeds > 0")
-
-            if self.config.class_embed_type == "timestep":
-                class_labels = self.time_proj(class_labels)
-
-            class_emb = self.class_embedding(class_labels).to(dtype=self.dtype)
-            emb = emb + class_emb
-
-        if self.config.addition_embed_type is not None:
-            if self.config.addition_embed_type == "text":
-                aug_emb = self.add_embedding(encoder_hidden_states)
-
-            elif self.config.addition_embed_type == "text_time":
-                if "text_embeds" not in added_cond_kwargs:
-                    raise ValueError(
-                        f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `text_embeds` to be passed in `added_cond_kwargs`"
-                    )
-                text_embeds = added_cond_kwargs.get("text_embeds")
-                if "time_ids" not in added_cond_kwargs:
-                    raise ValueError(
-                        f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `time_ids` to be passed in `added_cond_kwargs`"
-                    )
-                time_ids = added_cond_kwargs.get("time_ids")
-                time_embeds = self.add_time_proj(time_ids.flatten())
-                time_embeds = time_embeds.reshape((text_embeds.shape[0], -1))
-
-                add_embeds = torch.concat([text_embeds, time_embeds], dim=-1)
-                add_embeds = add_embeds.to(emb.dtype)
-                aug_emb = self.add_embedding(add_embeds)
-
-        emb = emb + aug_emb if aug_emb is not None else emb
-
-        # 2. pre-process
-        sample = self.conv_in(sample)
-
-        controlnet_cond = self.controlnet_cond_embedding(controlnet_cond)
-        sample = sample + controlnet_cond
-
-        # 3. down
-        down_block_res_samples = (sample,)
-        for downsample_block in self.down_blocks:
-            if hasattr(downsample_block, "has_cross_attention") and downsample_block.has_cross_attention:
-                sample, res_samples = downsample_block(
-                    hidden_states=sample,
-                    temb=emb,
-                    encoder_hidden_states=encoder_hidden_states,
-                    attention_mask=attention_mask,
-                    cross_attention_kwargs=cross_attention_kwargs,
-                )
-            else:
-                sample, res_samples = downsample_block(hidden_states=sample, temb=emb)
-
-            down_block_res_samples += res_samples
-
-        # 4. mid
-        if self.mid_block is not None:
-            if hasattr(self.mid_block, "has_cross_attention") and self.mid_block.has_cross_attention:
-                sample = self.mid_block(
-                    sample,
-                    emb,
-                    encoder_hidden_states=encoder_hidden_states,
-                    attention_mask=attention_mask,
-                    cross_attention_kwargs=cross_attention_kwargs,
-                )
-            else:
-                sample = self.mid_block(sample, emb)
-
-        # 5. Control net blocks
-
-        controlnet_down_block_res_samples = ()
-
-        for down_block_res_sample, controlnet_block in zip(down_block_res_samples, self.controlnet_down_blocks):
-            down_block_res_sample = controlnet_block(down_block_res_sample)
-            controlnet_down_block_res_samples = controlnet_down_block_res_samples + (down_block_res_sample,)
-
-        down_block_res_samples = controlnet_down_block_res_samples
-
-        mid_block_res_sample = self.controlnet_mid_block(sample)
-
-        # 6. scaling
-        if guess_mode and not self.config.global_pool_conditions:
-            scales = torch.logspace(-1, 0, len(down_block_res_samples) + 1, device=sample.device)  # 0.1 to 1.0
-            scales = scales * conditioning_scale
-            down_block_res_samples = [sample * scale for sample, scale in zip(down_block_res_samples, scales)]
-            mid_block_res_sample = mid_block_res_sample * scales[-1]  # last one
-        else:
-            down_block_res_samples = [sample * conditioning_scale for sample in down_block_res_samples]
-            mid_block_res_sample = mid_block_res_sample * conditioning_scale
-
-        if self.config.global_pool_conditions:
-            down_block_res_samples = [
-                torch.mean(sample, dim=(2, 3), keepdim=True) for sample in down_block_res_samples
-            ]
-            mid_block_res_sample = torch.mean(mid_block_res_sample, dim=(2, 3), keepdim=True)
-
-        if not return_dict:
-            return (down_block_res_samples, mid_block_res_sample)
-
-        return ControlNetOutput(
-            down_block_res_samples=down_block_res_samples, mid_block_res_sample=mid_block_res_sample
-        )
-
-
-def zero_module(module):
-    for p in module.parameters():
-        nn.init.zeros_(p)
-    return module

kolors/models/modeling_chatglm.py

@@ -1,1298 +0,0 @@
-""" PyTorch ChatGLM model. """
-
-import math
-import copy
-import warnings
-import re
-import sys
-
-import torch
-import torch.utils.checkpoint
-import torch.nn.functional as F
-from torch import nn
-from torch.nn import CrossEntropyLoss, LayerNorm
-from torch.nn import CrossEntropyLoss, LayerNorm, MSELoss, BCEWithLogitsLoss
-from torch.nn.utils import skip_init
-from typing import Optional, Tuple, Union, List, Callable, Dict, Any
-from copy import deepcopy
-
-from transformers.modeling_outputs import (
-    BaseModelOutputWithPast,
-    CausalLMOutputWithPast,
-    SequenceClassifierOutputWithPast,
-)
-from transformers.modeling_utils import PreTrainedModel
-from transformers.utils import logging
-from transformers.generation.logits_process import LogitsProcessor
-from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig, ModelOutput
-
-try:
-    from .configuration_chatglm import ChatGLMConfig
-except:
-    from configuration_chatglm import ChatGLMConfig
-
-
-# flags required to enable jit fusion kernels
-
-if sys.platform != 'darwin':
-    torch._C._jit_set_profiling_mode(False)
-    torch._C._jit_set_profiling_executor(False)
-    torch._C._jit_override_can_fuse_on_cpu(True)
-    torch._C._jit_override_can_fuse_on_gpu(True)
-
-logger = logging.get_logger(__name__)
-
-_CHECKPOINT_FOR_DOC = "THUDM/ChatGLM"
-_CONFIG_FOR_DOC = "ChatGLM6BConfig"
-
-CHATGLM_6B_PRETRAINED_MODEL_ARCHIVE_LIST = [
-    "THUDM/chatglm3-6b-base",
-    # See all ChatGLM models at https://huggingface.co/models?filter=chatglm
-]
-
-
-def default_init(cls, *args, **kwargs):
-    return cls(*args, **kwargs)
-
-
-class InvalidScoreLogitsProcessor(LogitsProcessor):
-    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor:
-        if torch.isnan(scores).any() or torch.isinf(scores).any():
-            scores.zero_()
-            scores[..., 5] = 5e4
-        return scores
-
-
-class PrefixEncoder(torch.nn.Module):
-    """
-    The torch.nn model to encode the prefix
-    Input shape: (batch-size, prefix-length)
-    Output shape: (batch-size, prefix-length, 2*layers*hidden)
-    """
-
-    def __init__(self, config: ChatGLMConfig):
-        super().__init__()
-        self.prefix_projection = config.prefix_projection
-        if self.prefix_projection:
-            # Use a two-layer MLP to encode the prefix
-            kv_size = config.num_layers * config.kv_channels * config.multi_query_group_num * 2
-            self.embedding = torch.nn.Embedding(config.pre_seq_len, kv_size)
-            self.trans = torch.nn.Sequential(
-                torch.nn.Linear(kv_size, config.hidden_size),
-                torch.nn.Tanh(),
-                torch.nn.Linear(config.hidden_size, kv_size)
-            )
-        else:
-            self.embedding = torch.nn.Embedding(config.pre_seq_len,
-                                                config.num_layers * config.kv_channels * config.multi_query_group_num * 2)
-
-    def forward(self, prefix: torch.Tensor):
-        if self.prefix_projection:
-            prefix_tokens = self.embedding(prefix)
-            past_key_values = self.trans(prefix_tokens)
-        else:
-            past_key_values = self.embedding(prefix)
-        return past_key_values
-
-
-def split_tensor_along_last_dim(
-        tensor: torch.Tensor,
-        num_partitions: int,
-        contiguous_split_chunks: bool = False,
-) -> List[torch.Tensor]:
-    """Split a tensor along its last dimension.
-
-    Arguments:
-        tensor: input tensor.
-        num_partitions: number of partitions to split the tensor
-        contiguous_split_chunks: If True, make each chunk contiguous
-                                 in memory.
-
-    Returns:
-        A list of Tensors
-    """
-    # Get the size and dimension.
-    last_dim = tensor.dim() - 1
-    last_dim_size = tensor.size()[last_dim] // num_partitions
-    # Split.
-    tensor_list = torch.split(tensor, last_dim_size, dim=last_dim)
-    # Note: torch.split does not create contiguous tensors by default.
-    if contiguous_split_chunks:
-        return tuple(chunk.contiguous() for chunk in tensor_list)
-
-    return tensor_list
-
-
-class RotaryEmbedding(nn.Module):
-    def __init__(self, dim, original_impl=False, device=None, dtype=None):
-        super().__init__()
-        inv_freq = 1.0 / (10000 ** (torch.arange(0, dim, 2, device=device).to(dtype=dtype) / dim))
-        self.register_buffer("inv_freq", inv_freq)
-        self.dim = dim
-        self.original_impl = original_impl
-
-    def forward_impl(
-            self, seq_len: int, n_elem: int, dtype: torch.dtype, device: torch.device, base: int = 10000
-    ):
-        """Enhanced Transformer with Rotary Position Embedding.
-
-        Derived from: https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/
-        transformers/rope/__init__.py. MIT License:
-        https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/license.
-        """
-        # $\Theta = {\theta_i = 10000^{\frac{2(i-1)}{d}}, i \in [1, 2, ..., \frac{d}{2}]}$
-        theta = 1.0 / (base ** (torch.arange(0, n_elem, 2, dtype=torch.float, device=device) / n_elem))
-
-        # Create position indexes `[0, 1, ..., seq_len - 1]`
-        seq_idx = torch.arange(seq_len, dtype=torch.float, device=device)
-
-        # Calculate the product of position index and $\theta_i$
-        idx_theta = torch.outer(seq_idx, theta).float()
-
-        cache = torch.stack([torch.cos(idx_theta), torch.sin(idx_theta)], dim=-1)
-
-        # this is to mimic the behaviour of complex32, else we will get different results
-        if dtype in (torch.float16, torch.bfloat16, torch.int8):
-            cache = cache.bfloat16() if dtype == torch.bfloat16 else cache.half()
-        return cache
-
-    def forward(self, max_seq_len, offset=0):
-        return self.forward_impl(
-            max_seq_len, self.dim, dtype=self.inv_freq.dtype, device=self.inv_freq.device
-        )
-
-
-@torch.jit.script
-def apply_rotary_pos_emb(x: torch.Tensor, rope_cache: torch.Tensor) -> torch.Tensor:
-    # x: [sq, b, np, hn]
-    sq, b, np, hn = x.size(0), x.size(1), x.size(2), x.size(3)
-    rot_dim = rope_cache.shape[-2] * 2
-    x, x_pass = x[..., :rot_dim], x[..., rot_dim:]
-    # truncate to support variable sizes
-    rope_cache = rope_cache[:sq]
-    xshaped = x.reshape(sq, -1, np, rot_dim // 2, 2)
-    rope_cache = rope_cache.view(sq, -1, 1, xshaped.size(3), 2)
-    x_out2 = torch.stack(
-        [
-            xshaped[..., 0] * rope_cache[..., 0] - xshaped[..., 1] * rope_cache[..., 1],
-            xshaped[..., 1] * rope_cache[..., 0] + xshaped[..., 0] * rope_cache[..., 1],
-        ],
-        -1,
-    )
-    x_out2 = x_out2.flatten(3)
-    return torch.cat((x_out2, x_pass), dim=-1)
-
-
-class RMSNorm(torch.nn.Module):
-    def __init__(self, normalized_shape, eps=1e-5, device=None, dtype=None, **kwargs):
-        super().__init__()
-        self.weight = torch.nn.Parameter(torch.empty(normalized_shape, device=device, dtype=dtype))
-        self.eps = eps
-
-    def forward(self, hidden_states: torch.Tensor):
-        input_dtype = hidden_states.dtype
-        variance = hidden_states.to(torch.float32).pow(2).mean(-1, keepdim=True)
-        hidden_states = hidden_states * torch.rsqrt(variance + self.eps)
-
-        return (self.weight * hidden_states).to(input_dtype)
-
-
-class CoreAttention(torch.nn.Module):
-    def __init__(self, config: ChatGLMConfig, layer_number):
-        super(CoreAttention, self).__init__()
-
-        self.apply_query_key_layer_scaling = config.apply_query_key_layer_scaling
-        self.attention_softmax_in_fp32 = config.attention_softmax_in_fp32
-        if self.apply_query_key_layer_scaling:
-            self.attention_softmax_in_fp32 = True
-        self.layer_number = max(1, layer_number)
-
-        projection_size = config.kv_channels * config.num_attention_heads
-
-        # Per attention head and per partition values.
-        self.hidden_size_per_partition = projection_size
-        self.hidden_size_per_attention_head = projection_size // config.num_attention_heads
-        self.num_attention_heads_per_partition = config.num_attention_heads
-
-        coeff = None
-        self.norm_factor = math.sqrt(self.hidden_size_per_attention_head)
-        if self.apply_query_key_layer_scaling:
-            coeff = self.layer_number
-            self.norm_factor *= coeff
-        self.coeff = coeff
-
-        self.attention_dropout = torch.nn.Dropout(config.attention_dropout)
-
-    def forward(self, query_layer, key_layer, value_layer, attention_mask):
-        pytorch_major_version = int(torch.__version__.split('.')[0])
-        if pytorch_major_version >= 2:
-            query_layer, key_layer, value_layer = [k.permute(1, 2, 0, 3) for k in [query_layer, key_layer, value_layer]]
-            if attention_mask is None and query_layer.shape[2] == key_layer.shape[2]:
-                context_layer = torch.nn.functional.scaled_dot_product_attention(query_layer, key_layer, value_layer,
-                                                                                 is_causal=True)
-            else:
-                if attention_mask is not None:
-                    attention_mask = ~attention_mask
-                context_layer = torch.nn.functional.scaled_dot_product_attention(query_layer, key_layer, value_layer,
-                                                                                 attention_mask)
-            context_layer = context_layer.permute(2, 0, 1, 3)
-            new_context_layer_shape = context_layer.size()[:-2] + (self.hidden_size_per_partition,)
-            context_layer = context_layer.reshape(*new_context_layer_shape)
-        else:
-            # Raw attention scores
-
-            # [b, np, sq, sk]
-            output_size = (query_layer.size(1), query_layer.size(2), query_layer.size(0), key_layer.size(0))
-
-            # [sq, b, np, hn] -> [sq, b * np, hn]
-            query_layer = query_layer.view(output_size[2], output_size[0] * output_size[1], -1)
-            # [sk, b, np, hn] -> [sk, b * np, hn]
-            key_layer = key_layer.view(output_size[3], output_size[0] * output_size[1], -1)
-
-            # preallocting input tensor: [b * np, sq, sk]
-            matmul_input_buffer = torch.empty(
-                output_size[0] * output_size[1], output_size[2], output_size[3], dtype=query_layer.dtype,
-                device=query_layer.device
-            )
-
-            # Raw attention scores. [b * np, sq, sk]
-            matmul_result = torch.baddbmm(
-                matmul_input_buffer,
-                query_layer.transpose(0, 1),  # [b * np, sq, hn]
-                key_layer.transpose(0, 1).transpose(1, 2),  # [b * np, hn, sk]
-                beta=0.0,
-                alpha=(1.0 / self.norm_factor),
-            )
-
-            # change view to [b, np, sq, sk]
-            attention_scores = matmul_result.view(*output_size)
-
-            # ===========================
-            # Attention probs and dropout
-            # ===========================
-
-            # attention scores and attention mask [b, np, sq, sk]
-            if self.attention_softmax_in_fp32:
-                attention_scores = attention_scores.float()
-            if self.coeff is not None:
-                attention_scores = attention_scores * self.coeff
-            if attention_mask is None and attention_scores.shape[2] == attention_scores.shape[3]:
-                attention_mask = torch.ones(output_size[0], 1, output_size[2], output_size[3],
-                                            device=attention_scores.device, dtype=torch.bool)
-                attention_mask.tril_()
-                attention_mask = ~attention_mask
-            if attention_mask is not None:
-                attention_scores = attention_scores.masked_fill(attention_mask, float("-inf"))
-            attention_probs = F.softmax(attention_scores, dim=-1)
-            attention_probs = attention_probs.type_as(value_layer)
-
-            # This is actually dropping out entire tokens to attend to, which might
-            # seem a bit unusual, but is taken from the original Transformer paper.
-            attention_probs = self.attention_dropout(attention_probs)
-            # =========================
-            # Context layer. [sq, b, hp]
-            # =========================
-
-            # value_layer -> context layer.
-            # [sk, b, np, hn] --> [b, np, sq, hn]
-
-            # context layer shape: [b, np, sq, hn]
-            output_size = (value_layer.size(1), value_layer.size(2), query_layer.size(0), value_layer.size(3))
-            # change view [sk, b * np, hn]
-            value_layer = value_layer.view(value_layer.size(0), output_size[0] * output_size[1], -1)
-            # change view [b * np, sq, sk]
-            attention_probs = attention_probs.view(output_size[0] * output_size[1], output_size[2], -1)
-            # matmul: [b * np, sq, hn]
-            context_layer = torch.bmm(attention_probs, value_layer.transpose(0, 1))
-            # change view [b, np, sq, hn]
-            context_layer = context_layer.view(*output_size)
-            # [b, np, sq, hn] --> [sq, b, np, hn]
-            context_layer = context_layer.permute(2, 0, 1, 3).contiguous()
-            # [sq, b, np, hn] --> [sq, b, hp]
-            new_context_layer_shape = context_layer.size()[:-2] + (self.hidden_size_per_partition,)
-            context_layer = context_layer.view(*new_context_layer_shape)
-
-        return context_layer
-
-
-class SelfAttention(torch.nn.Module):
-    """Parallel self-attention layer abstract class.
-
-    Self-attention layer takes input with size [s, b, h]
-    and returns output of the same size.
-    """
-
-    def __init__(self, config: ChatGLMConfig, layer_number, device=None):
-        super(SelfAttention, self).__init__()
-        self.layer_number = max(1, layer_number)
-
-        self.projection_size = config.kv_channels * config.num_attention_heads
-
-        # Per attention head and per partition values.
-        self.hidden_size_per_attention_head = self.projection_size // config.num_attention_heads
-        self.num_attention_heads_per_partition = config.num_attention_heads
-
-        self.multi_query_attention = config.multi_query_attention
-        self.qkv_hidden_size = 3 * self.projection_size
-        if self.multi_query_attention:
-            self.num_multi_query_groups_per_partition = config.multi_query_group_num
-            self.qkv_hidden_size = (
-                    self.projection_size + 2 * self.hidden_size_per_attention_head * config.multi_query_group_num
-            )
-        self.query_key_value = nn.Linear(config.hidden_size, self.qkv_hidden_size,
-                                         bias=config.add_bias_linear or config.add_qkv_bias,
-                                         device=device, **_config_to_kwargs(config)
-                                         )
-
-        self.core_attention = CoreAttention(config, self.layer_number)
-
-        # Output.
-        self.dense = nn.Linear(self.projection_size, config.hidden_size, bias=config.add_bias_linear,
-                               device=device, **_config_to_kwargs(config)
-                               )
-
-    def _allocate_memory(self, inference_max_sequence_len, batch_size, device=None, dtype=None):
-        if self.multi_query_attention:
-            num_attention_heads = self.num_multi_query_groups_per_partition
-        else:
-            num_attention_heads = self.num_attention_heads_per_partition
-        return torch.empty(
-            inference_max_sequence_len,
-            batch_size,
-            num_attention_heads,
-            self.hidden_size_per_attention_head,
-            dtype=dtype,
-            device=device,
-        )
-
-    def forward(
-            self, hidden_states, attention_mask, rotary_pos_emb, kv_cache=None, use_cache=True
-    ):
-        # hidden_states: [sq, b, h]
-
-        # =================================================
-        # Pre-allocate memory for key-values for inference.
-        # =================================================
-        # =====================
-        # Query, Key, and Value
-        # =====================
-
-        # Attention heads [sq, b, h] --> [sq, b, (np * 3 * hn)]
-        mixed_x_layer = self.query_key_value(hidden_states)
-
-        if self.multi_query_attention:
-            (query_layer, key_layer, value_layer) = mixed_x_layer.split(
-                [
-                    self.num_attention_heads_per_partition * self.hidden_size_per_attention_head,
-                    self.num_multi_query_groups_per_partition * self.hidden_size_per_attention_head,
-                    self.num_multi_query_groups_per_partition * self.hidden_size_per_attention_head,
-                ],
-                dim=-1,
-            )
-            query_layer = query_layer.view(
-                query_layer.size()[:-1] + (self.num_attention_heads_per_partition, self.hidden_size_per_attention_head)
-            )
-            key_layer = key_layer.view(
-                key_layer.size()[:-1] + (self.num_multi_query_groups_per_partition, self.hidden_size_per_attention_head)
-            )
-            value_layer = value_layer.view(
-                value_layer.size()[:-1]
-                + (self.num_multi_query_groups_per_partition, self.hidden_size_per_attention_head)
-            )
-        else:
-            new_tensor_shape = mixed_x_layer.size()[:-1] + \
-                               (self.num_attention_heads_per_partition,
-                                3 * self.hidden_size_per_attention_head)
-            mixed_x_layer = mixed_x_layer.view(*new_tensor_shape)
-
-            # [sq, b, np, 3 * hn] --> 3 [sq, b, np, hn]
-            (query_layer, key_layer, value_layer) = split_tensor_along_last_dim(mixed_x_layer, 3)
-
-        # apply relative positional encoding (rotary embedding)
-        if rotary_pos_emb is not None:
-            query_layer = apply_rotary_pos_emb(query_layer, rotary_pos_emb)
-            key_layer = apply_rotary_pos_emb(key_layer, rotary_pos_emb)
-
-        # adjust key and value for inference
-        if kv_cache is not None:
-            cache_k, cache_v = kv_cache
-            key_layer = torch.cat((cache_k, key_layer), dim=0)
-            value_layer = torch.cat((cache_v, value_layer), dim=0)
-        if use_cache:
-            kv_cache = (key_layer, value_layer)
-        else:
-            kv_cache = None
-
-        if self.multi_query_attention:
-            key_layer = key_layer.unsqueeze(-2)
-            key_layer = key_layer.expand(
-                -1, -1, -1, self.num_attention_heads_per_partition // self.num_multi_query_groups_per_partition, -1
-            )
-            key_layer = key_layer.contiguous().view(
-                key_layer.size()[:2] + (self.num_attention_heads_per_partition, self.hidden_size_per_attention_head)
-            )
-            value_layer = value_layer.unsqueeze(-2)
-            value_layer = value_layer.expand(
-                -1, -1, -1, self.num_attention_heads_per_partition // self.num_multi_query_groups_per_partition, -1
-            )
-            value_layer = value_layer.contiguous().view(
-                value_layer.size()[:2] + (self.num_attention_heads_per_partition, self.hidden_size_per_attention_head)
-            )
-
-        # ==================================
-        # core attention computation
-        # ==================================
-
-        context_layer = self.core_attention(query_layer, key_layer, value_layer, attention_mask)
-
-        # =================
-        # Output. [sq, b, h]
-        # =================
-
-        output = self.dense(context_layer)
-
-        return output, kv_cache
-
-
-def _config_to_kwargs(args):
-    common_kwargs = {
-        "dtype": args.torch_dtype,
-    }
-    return common_kwargs
-
-
-class MLP(torch.nn.Module):
-    """MLP.
-
-    MLP will take the input with h hidden state, project it to 4*h
-    hidden dimension, perform nonlinear transformation, and project the
-    state back into h hidden dimension.
-    """
-
-    def __init__(self, config: ChatGLMConfig, device=None):
-        super(MLP, self).__init__()
-
-        self.add_bias = config.add_bias_linear
-
-        # Project to 4h. If using swiglu double the output width, see https://arxiv.org/pdf/2002.05202.pdf
-        self.dense_h_to_4h = nn.Linear(
-            config.hidden_size,
-            config.ffn_hidden_size * 2,
-            bias=self.add_bias,
-            device=device,
-            **_config_to_kwargs(config)
-        )
-
-        def swiglu(x):
-            x = torch.chunk(x, 2, dim=-1)
-            return F.silu(x[0]) * x[1]
-
-        self.activation_func = swiglu
-
-        # Project back to h.
-        self.dense_4h_to_h = nn.Linear(
-            config.ffn_hidden_size,
-            config.hidden_size,
-            bias=self.add_bias,
-            device=device,
-            **_config_to_kwargs(config)
-        )
-
-    def forward(self, hidden_states):
-        # [s, b, 4hp]
-        intermediate_parallel = self.dense_h_to_4h(hidden_states)
-        intermediate_parallel = self.activation_func(intermediate_parallel)
-        # [s, b, h]
-        output = self.dense_4h_to_h(intermediate_parallel)
-        return output
-
-
-class GLMBlock(torch.nn.Module):
-    """A single transformer layer.
-
-    Transformer layer takes input with size [s, b, h] and returns an
-    output of the same size.
-    """
-
-    def __init__(self, config: ChatGLMConfig, layer_number, device=None):
-        super(GLMBlock, self).__init__()
-        self.layer_number = layer_number
-
-        self.apply_residual_connection_post_layernorm = config.apply_residual_connection_post_layernorm
-
-        self.fp32_residual_connection = config.fp32_residual_connection
-
-        LayerNormFunc = RMSNorm if config.rmsnorm else LayerNorm
-        # Layernorm on the input data.
-        self.input_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device,
-                                             dtype=config.torch_dtype)
-
-        # Self attention.
-        self.self_attention = SelfAttention(config, layer_number, device=device)
-        self.hidden_dropout = config.hidden_dropout
-
-        # Layernorm on the attention output
-        self.post_attention_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device,
-                                                      dtype=config.torch_dtype)
-
-        # MLP
-        self.mlp = MLP(config, device=device)
-
-    def forward(
-            self, hidden_states, attention_mask, rotary_pos_emb, kv_cache=None, use_cache=True,
-    ):
-        # hidden_states: [s, b, h]
-
-        # Layer norm at the beginning of the transformer layer.
-        layernorm_output = self.input_layernorm(hidden_states)
-        # Self attention.
-        attention_output, kv_cache = self.self_attention(
-            layernorm_output,
-            attention_mask,
-            rotary_pos_emb,
-            kv_cache=kv_cache,
-            use_cache=use_cache
-        )
-
-        # Residual connection.
-        if self.apply_residual_connection_post_layernorm:
-            residual = layernorm_output
-        else:
-            residual = hidden_states
-
-        layernorm_input = torch.nn.functional.dropout(attention_output, p=self.hidden_dropout, training=self.training)
-        layernorm_input = residual + layernorm_input
-
-        # Layer norm post the self attention.
-        layernorm_output = self.post_attention_layernorm(layernorm_input)
-
-        # MLP.
-        mlp_output = self.mlp(layernorm_output)
-
-        # Second residual connection.
-        if self.apply_residual_connection_post_layernorm:
-            residual = layernorm_output
-        else:
-            residual = layernorm_input
-
-        output = torch.nn.functional.dropout(mlp_output, p=self.hidden_dropout, training=self.training)
-        output = residual + output
-
-        return output, kv_cache
-
-
-class GLMTransformer(torch.nn.Module):
-    """Transformer class."""
-
-    def __init__(self, config: ChatGLMConfig, device=None):
-        super(GLMTransformer, self).__init__()
-
-        self.fp32_residual_connection = config.fp32_residual_connection
-        self.post_layer_norm = config.post_layer_norm
-
-        # Number of layers.
-        self.num_layers = config.num_layers
-
-        # Transformer layers.
-        def build_layer(layer_number):
-            return GLMBlock(config, layer_number, device=device)
-
-        self.layers = torch.nn.ModuleList([build_layer(i + 1) for i in range(self.num_layers)])
-
-        if self.post_layer_norm:
-            LayerNormFunc = RMSNorm if config.rmsnorm else LayerNorm
-            # Final layer norm before output.
-            self.final_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device,
-                                                 dtype=config.torch_dtype)
-
-        self.gradient_checkpointing = False
-
-    def _get_layer(self, layer_number):
-        return self.layers[layer_number]
-
-    def forward(
-            self, hidden_states, attention_mask, rotary_pos_emb, kv_caches=None,
-            use_cache: Optional[bool] = True,
-            output_hidden_states: Optional[bool] = False,
-    ):
-        if not kv_caches:
-            kv_caches = [None for _ in range(self.num_layers)]
-        presents = () if use_cache else None
-        if self.gradient_checkpointing and self.training:
-            if use_cache:
-                logger.warning_once(
-                    "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
-                )
-                use_cache = False
-
-        all_self_attentions = None
-        all_hidden_states = () if output_hidden_states else None
-        for index in range(self.num_layers):
-            if output_hidden_states:
-                all_hidden_states = all_hidden_states + (hidden_states,)
-
-            layer = self._get_layer(index)
-            if self.gradient_checkpointing and self.training:
-                layer_ret = torch.utils.checkpoint.checkpoint(
-                    layer,
-                    hidden_states,
-                    attention_mask,
-                    rotary_pos_emb,
-                    kv_caches[index],
-                    use_cache
-                )
-            else:
-                layer_ret = layer(
-                    hidden_states,
-                    attention_mask,
-                    rotary_pos_emb,
-                    kv_cache=kv_caches[index],
-                    use_cache=use_cache
-                )
-            hidden_states, kv_cache = layer_ret
-            if use_cache:
-                presents = presents + (kv_cache,)
-
-        if output_hidden_states:
-            all_hidden_states = all_hidden_states + (hidden_states,)
-
-        # Final layer norm.
-        if self.post_layer_norm:
-            hidden_states = self.final_layernorm(hidden_states)
-
-        return hidden_states, presents, all_hidden_states, all_self_attentions
-
-
-class ChatGLMPreTrainedModel(PreTrainedModel):
-    """
-    An abstract class to handle weights initialization and
-    a simple interface for downloading and loading pretrained models.
-    """
-
-    is_parallelizable = False
-    supports_gradient_checkpointing = True
-    config_class = ChatGLMConfig
-    base_model_prefix = "transformer"
-    _no_split_modules = ["GLMBlock"]
-
-    def _init_weights(self, module: nn.Module):
-        """Initialize the weights."""
-        return
-
-    def get_masks(self, input_ids, past_key_values, padding_mask=None):
-        batch_size, seq_length = input_ids.shape
-        full_attention_mask = torch.ones(batch_size, seq_length, seq_length, device=input_ids.device)
-        full_attention_mask.tril_()
-        past_length = 0
-        if past_key_values:
-            past_length = past_key_values[0][0].shape[0]
-        if past_length:
-            full_attention_mask = torch.cat((torch.ones(batch_size, seq_length, past_length,
-                                                        device=input_ids.device), full_attention_mask), dim=-1)
-        if padding_mask is not None:
-            full_attention_mask = full_attention_mask * padding_mask.unsqueeze(1)
-        if not past_length and padding_mask is not None:
-            full_attention_mask -= padding_mask.unsqueeze(-1) - 1
-        full_attention_mask = (full_attention_mask < 0.5).bool()
-        full_attention_mask.unsqueeze_(1)
-        return full_attention_mask
-
-    def get_position_ids(self, input_ids, device):
-        batch_size, seq_length = input_ids.shape
-        position_ids = torch.arange(seq_length, dtype=torch.long, device=device).unsqueeze(0).repeat(batch_size, 1)
-        return position_ids
-
-    def _set_gradient_checkpointing(self, module, value=False):
-        if isinstance(module, GLMTransformer):
-            module.gradient_checkpointing = value
-
-
-class Embedding(torch.nn.Module):
-    """Language model embeddings."""
-
-    def __init__(self, config: ChatGLMConfig, device=None):
-        super(Embedding, self).__init__()
-
-        self.hidden_size = config.hidden_size
-        # Word embeddings (parallel).
-        self.word_embeddings = nn.Embedding(
-            config.padded_vocab_size,
-            self.hidden_size,
-            dtype=config.torch_dtype,
-            device=device
-        )
-        self.fp32_residual_connection = config.fp32_residual_connection
-
-    def forward(self, input_ids):
-        # Embeddings.
-        words_embeddings = self.word_embeddings(input_ids)
-        embeddings = words_embeddings
-        # Data format change to avoid explicit tranposes : [b s h] --> [s b h].
-        embeddings = embeddings.transpose(0, 1).contiguous()
-        # If the input flag for fp32 residual connection is set, convert for float.
-        if self.fp32_residual_connection:
-            embeddings = embeddings.float()
-        return embeddings
-
-
-class ChatGLMModel(ChatGLMPreTrainedModel):
-    def __init__(self, config: ChatGLMConfig, device=None, empty_init=True):
-        super().__init__(config)
-        if empty_init:
-            init_method = skip_init
-        else:
-            init_method = default_init
-        init_kwargs = {}
-        if device is not None:
-            init_kwargs["device"] = device
-        self.embedding = init_method(Embedding, config, **init_kwargs)
-        self.num_layers = config.num_layers
-        self.multi_query_group_num = config.multi_query_group_num
-        self.kv_channels = config.kv_channels
-
-        # Rotary positional embeddings
-        self.seq_length = config.seq_length
-        rotary_dim = (
-            config.hidden_size // config.num_attention_heads if config.kv_channels is None else config.kv_channels
-        )
-
-        self.rotary_pos_emb = RotaryEmbedding(rotary_dim // 2, original_impl=config.original_rope, device=device,
-                                              dtype=config.torch_dtype)
-        self.encoder = init_method(GLMTransformer, config, **init_kwargs)
-        self.output_layer = init_method(nn.Linear, config.hidden_size, config.padded_vocab_size, bias=False,
-                                        dtype=config.torch_dtype, **init_kwargs)
-        self.pre_seq_len = config.pre_seq_len
-        self.prefix_projection = config.prefix_projection
-        if self.pre_seq_len is not None:
-            for param in self.parameters():
-                param.requires_grad = False
-            self.prefix_tokens = torch.arange(self.pre_seq_len).long()
-            self.prefix_encoder = PrefixEncoder(config)
-            self.dropout = torch.nn.Dropout(0.1)
-
-    def get_input_embeddings(self):
-        return self.embedding.word_embeddings
-
-    def get_prompt(self, batch_size, device, dtype=torch.half):
-        prefix_tokens = self.prefix_tokens.unsqueeze(0).expand(batch_size, -1).to(device)
-        past_key_values = self.prefix_encoder(prefix_tokens).type(dtype)
-        past_key_values = past_key_values.view(
-            batch_size,
-            self.pre_seq_len,
-            self.num_layers * 2,
-            self.multi_query_group_num,
-            self.kv_channels
-        )
-        # seq_len, b, nh, hidden_size
-        past_key_values = self.dropout(past_key_values)
-        past_key_values = past_key_values.permute([2, 1, 0, 3, 4]).split(2)
-        return past_key_values
-
-    def forward(
-            self,
-            input_ids,
-            position_ids: Optional[torch.Tensor] = None,
-            attention_mask: Optional[torch.BoolTensor] = None,
-            full_attention_mask: Optional[torch.BoolTensor] = None,
-            past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None,
-            inputs_embeds: Optional[torch.Tensor] = None,
-            use_cache: Optional[bool] = None,
-            output_hidden_states: Optional[bool] = None,
-            return_dict: Optional[bool] = None,
-    ):
-        output_hidden_states = (
-            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
-        )
-        use_cache = use_cache if use_cache is not None else self.config.use_cache
-        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
-
-        batch_size, seq_length = input_ids.shape
-
-        if inputs_embeds is None:
-            inputs_embeds = self.embedding(input_ids)
-
-        if self.pre_seq_len is not None:
-            if past_key_values is None:
-                past_key_values = self.get_prompt(batch_size=batch_size, device=input_ids.device,
-                                                  dtype=inputs_embeds.dtype)
-            if attention_mask is not None:
-                attention_mask = torch.cat([attention_mask.new_ones((batch_size, self.pre_seq_len)),
-                                            attention_mask], dim=-1)
-
-        if full_attention_mask is None:
-            if (attention_mask is not None and not attention_mask.all()) or (past_key_values and seq_length != 1):
-                full_attention_mask = self.get_masks(input_ids, past_key_values, padding_mask=attention_mask)
-
-        # Rotary positional embeddings
-        rotary_pos_emb = self.rotary_pos_emb(self.seq_length)
-        if position_ids is not None:
-            rotary_pos_emb = rotary_pos_emb[position_ids]
-        else:
-            rotary_pos_emb = rotary_pos_emb[None, :seq_length]
-        rotary_pos_emb = rotary_pos_emb.transpose(0, 1).contiguous()
-
-        # Run encoder.
-        hidden_states, presents, all_hidden_states, all_self_attentions = self.encoder(
-            inputs_embeds, full_attention_mask, rotary_pos_emb=rotary_pos_emb,
-            kv_caches=past_key_values, use_cache=use_cache, output_hidden_states=output_hidden_states
-        )
-
-        if not return_dict:
-            return tuple(v for v in [hidden_states, presents, all_hidden_states, all_self_attentions] if v is not None)
-
-        return BaseModelOutputWithPast(
-            last_hidden_state=hidden_states,
-            past_key_values=presents,
-            hidden_states=all_hidden_states,
-            attentions=all_self_attentions,
-        )
-
-    def quantize(self, weight_bit_width: int):
-        from .quantization import quantize
-        quantize(self.encoder, weight_bit_width)
-        return self
-
-
-class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
-    def __init__(self, config: ChatGLMConfig, empty_init=True, device=None):
-        super().__init__(config)
-
-        self.max_sequence_length = config.max_length
-        self.transformer = ChatGLMModel(config, empty_init=empty_init, device=device)
-        self.config = config
-        self.quantized = False
-
-        if self.config.quantization_bit:
-            self.quantize(self.config.quantization_bit, empty_init=True)
-
-    def _update_model_kwargs_for_generation(
-            self,
-            outputs: ModelOutput,
-            model_kwargs: Dict[str, Any],
-            is_encoder_decoder: bool = False,
-            standardize_cache_format: bool = False,
-    ) -> Dict[str, Any]:
-        # update past_key_values
-        model_kwargs["past_key_values"] = self._extract_past_from_model_output(
-            outputs, standardize_cache_format=standardize_cache_format
-        )
-
-        # update attention mask
-        if "attention_mask" in model_kwargs:
-            attention_mask = model_kwargs["attention_mask"]
-            model_kwargs["attention_mask"] = torch.cat(
-                [attention_mask, attention_mask.new_ones((attention_mask.shape[0], 1))], dim=-1
-            )
-
-        # update position ids
-        if "position_ids" in model_kwargs:
-            position_ids = model_kwargs["position_ids"]
-            new_position_id = position_ids[..., -1:].clone()
-            new_position_id += 1
-            model_kwargs["position_ids"] = torch.cat(
-                [position_ids, new_position_id], dim=-1
-            )
-
-        model_kwargs["is_first_forward"] = False
-        return model_kwargs
-
-    def prepare_inputs_for_generation(
-            self,
-            input_ids: torch.LongTensor,
-            past_key_values: Optional[torch.Tensor] = None,
-            attention_mask: Optional[torch.Tensor] = None,
-            position_ids: Optional[torch.Tensor] = None,
-            use_cache: Optional[bool] = None,
-            is_first_forward: bool = True,
-            **kwargs
-    ) -> dict:
-        # only last token for input_ids if past is not None
-        if position_ids is None:
-            position_ids = self.get_position_ids(input_ids, device=input_ids.device)
-        if not is_first_forward:
-            if past_key_values is not None:
-                position_ids = position_ids[..., -1:]
-                input_ids = input_ids[:, -1:]
-        return {
-            "input_ids": input_ids,
-            "past_key_values": past_key_values,
-            "position_ids": position_ids,
-            "attention_mask": attention_mask,
-            "return_last_logit": True,
-            "use_cache": use_cache
-        }
-
-    def forward(
-            self,
-            input_ids: Optional[torch.Tensor] = None,
-            position_ids: Optional[torch.Tensor] = None,
-            attention_mask: Optional[torch.Tensor] = None,
-            past_key_values: Optional[Tuple[torch.FloatTensor]] = None,
-            inputs_embeds: Optional[torch.Tensor] = None,
-            labels: Optional[torch.Tensor] = None,
-            use_cache: Optional[bool] = None,
-            output_attentions: Optional[bool] = None,
-            output_hidden_states: Optional[bool] = None,
-            return_dict: Optional[bool] = None,
-            return_last_logit: Optional[bool] = False,
-    ):
-        use_cache = use_cache if use_cache is not None else self.config.use_cache
-        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
-
-        transformer_outputs = self.transformer(
-            input_ids=input_ids,
-            position_ids=position_ids,
-            attention_mask=attention_mask,
-            past_key_values=past_key_values,
-            inputs_embeds=inputs_embeds,
-            use_cache=use_cache,
-            output_hidden_states=output_hidden_states,
-            return_dict=return_dict,
-        )
-
-        hidden_states = transformer_outputs[0]
-        if return_last_logit:
-            hidden_states = hidden_states[-1:]
-        lm_logits = self.transformer.output_layer(hidden_states)
-        lm_logits = lm_logits.transpose(0, 1).contiguous()
-
-        loss = None
-        if labels is not None:
-            lm_logits = lm_logits.to(torch.float32)
-
-            # Shift so that tokens < n predict n
-            shift_logits = lm_logits[..., :-1, :].contiguous()
-            shift_labels = labels[..., 1:].contiguous()
-            # Flatten the tokens
-            loss_fct = CrossEntropyLoss(ignore_index=-100)
-            loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))
-
-            lm_logits = lm_logits.to(hidden_states.dtype)
-            loss = loss.to(hidden_states.dtype)
-
-        if not return_dict:
-            output = (lm_logits,) + transformer_outputs[1:]
-            return ((loss,) + output) if loss is not None else output
-
-        return CausalLMOutputWithPast(
-            loss=loss,
-            logits=lm_logits,
-            past_key_values=transformer_outputs.past_key_values,
-            hidden_states=transformer_outputs.hidden_states,
-            attentions=transformer_outputs.attentions,
-        )
-
-    @staticmethod
-    def _reorder_cache(
-            past: Tuple[Tuple[torch.Tensor, torch.Tensor], ...], beam_idx: torch.LongTensor
-    ) -> Tuple[Tuple[torch.Tensor, torch.Tensor], ...]:
-        """
-        This function is used to re-order the `past_key_values` cache if [`~PreTrainedModel.beam_search`] or
-        [`~PreTrainedModel.beam_sample`] is called. This is required to match `past_key_values` with the correct
-        beam_idx at every generation step.
-
-        Output shares the same memory storage as `past`.
-        """
-        return tuple(
-            (
-                layer_past[0].index_select(1, beam_idx.to(layer_past[0].device)),
-                layer_past[1].index_select(1, beam_idx.to(layer_past[1].device)),
-            )
-            for layer_past in past
-        )
-
-    def process_response(self, output, history):
-        content = ""
-        history = deepcopy(history)
-        for response in output.split("<|assistant|>"):
-            metadata, content = response.split("\n", maxsplit=1)
-            if not metadata.strip():
-                content = content.strip()
-                history.append({"role": "assistant", "metadata": metadata, "content": content})
-                content = content.replace("[[训练时间]]", "2023年")
-            else:
-                history.append({"role": "assistant", "metadata": metadata, "content": content})
-                if history[0]["role"] == "system" and "tools" in history[0]:
-                    content = "\n".join(content.split("\n")[1:-1])
-                    def tool_call(**kwargs):
-                        return kwargs
-                    parameters = eval(content)
-                    content = {"name": metadata.strip(), "parameters": parameters}
-                else:
-                    content = {"name": metadata.strip(), "content": content}
-        return content, history
-
-    @torch.inference_mode()
-    def chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, role: str = "user",
-             max_length: int = 8192, num_beams=1, do_sample=True, top_p=0.8, temperature=0.8, logits_processor=None,
-             **kwargs):
-        if history is None:
-            history = []
-        if logits_processor is None:
-            logits_processor = LogitsProcessorList()
-        logits_processor.append(InvalidScoreLogitsProcessor())
-        gen_kwargs = {"max_length": max_length, "num_beams": num_beams, "do_sample": do_sample, "top_p": top_p,
-                      "temperature": temperature, "logits_processor": logits_processor, **kwargs}
-        inputs = tokenizer.build_chat_input(query, history=history, role=role)
-        inputs = inputs.to(self.device)
-        eos_token_id = [tokenizer.eos_token_id, tokenizer.get_command("<|user|>"),
-                        tokenizer.get_command("<|observation|>")]
-        outputs = self.generate(**inputs, **gen_kwargs, eos_token_id=eos_token_id)
-        outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):-1]
-        response = tokenizer.decode(outputs)
-        history.append({"role": role, "content": query})
-        response, history = self.process_response(response, history)
-        return response, history
-
-    @torch.inference_mode()
-    def stream_chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, role: str = "user",
-                    past_key_values=None,max_length: int = 8192, do_sample=True, top_p=0.8, temperature=0.8,
-                    logits_processor=None, return_past_key_values=False, **kwargs):
-        if history is None:
-            history = []
-        if logits_processor is None:
-            logits_processor = LogitsProcessorList()
-        logits_processor.append(InvalidScoreLogitsProcessor())
-        eos_token_id = [tokenizer.eos_token_id, tokenizer.get_command("<|user|>"),
-                        tokenizer.get_command("<|observation|>")]
-        gen_kwargs = {"max_length": max_length, "do_sample": do_sample, "top_p": top_p,
-                      "temperature": temperature, "logits_processor": logits_processor, **kwargs}
-        if past_key_values is None:
-            inputs = tokenizer.build_chat_input(query, history=history, role=role)
-        else:
-            inputs = tokenizer.build_chat_input(query, role=role)
-        inputs = inputs.to(self.device)
-        if past_key_values is not None:
-            past_length = past_key_values[0][0].shape[0]
-            if self.transformer.pre_seq_len is not None:
-                past_length -= self.transformer.pre_seq_len
-            inputs.position_ids += past_length
-            attention_mask = inputs.attention_mask
-            attention_mask = torch.cat((attention_mask.new_ones(1, past_length), attention_mask), dim=1)
-            inputs['attention_mask'] = attention_mask
-        history.append({"role": role, "content": query})
-        for outputs in self.stream_generate(**inputs, past_key_values=past_key_values,
-                                            eos_token_id=eos_token_id, return_past_key_values=return_past_key_values,
-                                            **gen_kwargs):
-            if return_past_key_values:
-                outputs, past_key_values = outputs
-            outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):-1]
-            response = tokenizer.decode(outputs)
-            if response and response[-1] != "�":
-                response, new_history = self.process_response(response, history)
-                if return_past_key_values:
-                    yield response, new_history, past_key_values
-                else:
-                    yield response, new_history
-
-    @torch.inference_mode()
-    def stream_generate(
-            self,
-            input_ids,
-            generation_config: Optional[GenerationConfig] = None,
-            logits_processor: Optional[LogitsProcessorList] = None,
-            stopping_criteria: Optional[StoppingCriteriaList] = None,
-            prefix_allowed_tokens_fn: Optional[Callable[[int, torch.Tensor], List[int]]] = None,
-            return_past_key_values=False,
-            **kwargs,
-    ):
-        batch_size, input_ids_seq_length = input_ids.shape[0], input_ids.shape[-1]
-
-        if generation_config is None:
-            generation_config = self.generation_config
-        generation_config = copy.deepcopy(generation_config)
-        model_kwargs = generation_config.update(**kwargs)
-        model_kwargs["use_cache"] = generation_config.use_cache
-        bos_token_id, eos_token_id = generation_config.bos_token_id, generation_config.eos_token_id
-
-        if isinstance(eos_token_id, int):
-            eos_token_id = [eos_token_id]
-        eos_token_id_tensor = torch.tensor(eos_token_id).to(input_ids.device) if eos_token_id is not None else None
-
-        has_default_max_length = kwargs.get("max_length") is None and generation_config.max_length is not None
-        if has_default_max_length and generation_config.max_new_tokens is None:
-            warnings.warn(
-                f"Using `max_length`'s default ({generation_config.max_length}) to control the generation length. "
-                "This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we"
-                " recommend using `max_new_tokens` to control the maximum length of the generation.",
-                UserWarning,
-            )
-        elif generation_config.max_new_tokens is not None:
-            generation_config.max_length = generation_config.max_new_tokens + input_ids_seq_length
-            if not has_default_max_length:
-                logger.warn(
-                    f"Both `max_new_tokens` (={generation_config.max_new_tokens}) and `max_length`(="
-                    f"{generation_config.max_length}) seem to have been set. `max_new_tokens` will take precedence. "
-                    "Please refer to the documentation for more information. "
-                    "(https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)",
-                    UserWarning,
-                )
-
-        if input_ids_seq_length >= generation_config.max_length:
-            input_ids_string = "decoder_input_ids" if self.config.is_encoder_decoder else "input_ids"
-            logger.warning(
-                f"Input length of {input_ids_string} is {input_ids_seq_length}, but `max_length` is set to"
-                f" {generation_config.max_length}. This can lead to unexpected behavior. You should consider"
-                " increasing `max_new_tokens`."
-            )
-
-        # 2. Set generation parameters if not already defined
-        logits_processor = logits_processor if logits_processor is not None else LogitsProcessorList()
-        stopping_criteria = stopping_criteria if stopping_criteria is not None else StoppingCriteriaList()
-
-        logits_processor = self._get_logits_processor(
-            generation_config=generation_config,
-            input_ids_seq_length=input_ids_seq_length,
-            encoder_input_ids=input_ids,
-            prefix_allowed_tokens_fn=prefix_allowed_tokens_fn,
-            logits_processor=logits_processor,
-        )
-
-        stopping_criteria = self._get_stopping_criteria(
-            generation_config=generation_config, stopping_criteria=stopping_criteria
-        )
-        logits_warper = self._get_logits_warper(generation_config)
-
-        unfinished_sequences = input_ids.new(input_ids.shape[0]).fill_(1)
-        scores = None
-        while True:
-            model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)
-            # forward pass to get next token
-            outputs = self(
-                **model_inputs,
-                return_dict=True,
-                output_attentions=False,
-                output_hidden_states=False,
-            )
-
-            next_token_logits = outputs.logits[:, -1, :]
-
-            # pre-process distribution
-            next_token_scores = logits_processor(input_ids, next_token_logits)
-            next_token_scores = logits_warper(input_ids, next_token_scores)
-
-            # sample
-            probs = nn.functional.softmax(next_token_scores, dim=-1)
-            if generation_config.do_sample:
-                next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1)
-            else:
-                next_tokens = torch.argmax(probs, dim=-1)
-            # update generated ids, model inputs, and length for next step
-            input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1)
-            model_kwargs = self._update_model_kwargs_for_generation(
-                outputs, model_kwargs, is_encoder_decoder=self.config.is_encoder_decoder
-            )
-            unfinished_sequences = unfinished_sequences.mul(
-                next_tokens.tile(eos_token_id_tensor.shape[0], 1).ne(eos_token_id_tensor.unsqueeze(1)).prod(dim=0)
-            )
-            if return_past_key_values:
-                yield input_ids, outputs.past_key_values
-            else:
-                yield input_ids
-            # stop when each sentence is finished, or if we exceed the maximum length
-            if unfinished_sequences.max() == 0 or stopping_criteria(input_ids, scores):
-                break
-
-    def quantize(self, bits: int, empty_init=False, device=None, **kwargs):
-        if bits == 0:
-            return
-
-        from .quantization import quantize
-
-        if self.quantized:
-            logger.info("Already quantized.")
-            return self
-
-        self.quantized = True
-
-        self.config.quantization_bit = bits
-
-        self.transformer.encoder = quantize(self.transformer.encoder, bits, empty_init=empty_init, device=device,
-                                            **kwargs)
-        return self
-
-
-class ChatGLMForSequenceClassification(ChatGLMPreTrainedModel):
-    def __init__(self, config: ChatGLMConfig, empty_init=True, device=None):
-        super().__init__(config)
-
-        self.num_labels = config.num_labels
-        self.transformer = ChatGLMModel(config, empty_init=empty_init, device=device)
-
-        self.classifier_head = nn.Linear(config.hidden_size, config.num_labels, bias=True, dtype=torch.half)
-        if config.classifier_dropout is not None:
-            self.dropout = nn.Dropout(config.classifier_dropout)
-        else:
-            self.dropout = None
-        self.config = config
-
-        if self.config.quantization_bit:
-            self.quantize(self.config.quantization_bit, empty_init=True)
-
-    def forward(
-            self,
-            input_ids: Optional[torch.LongTensor] = None,
-            position_ids: Optional[torch.LongTensor] = None,
-            attention_mask: Optional[torch.Tensor] = None,
-            full_attention_mask: Optional[torch.Tensor] = None,
-            past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None,
-            inputs_embeds: Optional[torch.LongTensor] = None,
-            labels: Optional[torch.LongTensor] = None,
-            use_cache: Optional[bool] = None,
-            output_hidden_states: Optional[bool] = None,
-            return_dict: Optional[bool] = None,
-    ) -> Union[Tuple[torch.Tensor, ...], SequenceClassifierOutputWithPast]:
-        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
-
-        transformer_outputs = self.transformer(
-            input_ids=input_ids,
-            position_ids=position_ids,
-            attention_mask=attention_mask,
-            full_attention_mask=full_attention_mask,
-            past_key_values=past_key_values,
-            inputs_embeds=inputs_embeds,
-            use_cache=use_cache,
-            output_hidden_states=output_hidden_states,
-            return_dict=return_dict,
-        )
-
-        hidden_states = transformer_outputs[0]
-        pooled_hidden_states = hidden_states[-1]
-        if self.dropout is not None:
-            pooled_hidden_states = self.dropout(pooled_hidden_states)
-        logits = self.classifier_head(pooled_hidden_states)
-
-        loss = None
-        if labels is not None:
-            if self.config.problem_type is None:
-                if self.num_labels == 1:
-                    self.config.problem_type = "regression"
-                elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
-                    self.config.problem_type = "single_label_classification"
-                else:
-                    self.config.problem_type = "multi_label_classification"
-
-            if self.config.problem_type == "regression":
-                loss_fct = MSELoss()
-                if self.num_labels == 1:
-                    loss = loss_fct(logits.squeeze().float(), labels.squeeze())
-                else:
-                    loss = loss_fct(logits.float(), labels)
-            elif self.config.problem_type == "single_label_classification":
-                loss_fct = CrossEntropyLoss()
-                loss = loss_fct(logits.view(-1, self.num_labels).float(), labels.view(-1))
-            elif self.config.problem_type == "multi_label_classification":
-                loss_fct = BCEWithLogitsLoss()
-                loss = loss_fct(logits.float(), labels.view(-1, self.num_labels))
-
-        if not return_dict:
-            output = (logits,) + transformer_outputs[1:]
-            return ((loss,) + output) if loss is not None else output
-
-        return SequenceClassifierOutputWithPast(
-            loss=loss,
-            logits=logits,
-            past_key_values=transformer_outputs.past_key_values,
-            hidden_states=transformer_outputs.hidden_states,
-            attentions=transformer_outputs.attentions,
-        )

kolors/models/tokenization_chatglm.py

@@ -1,300 +0,0 @@
-import json
-import os
-import re
-from typing import List, Optional, Union, Dict
-from sentencepiece import SentencePieceProcessor
-from transformers import PreTrainedTokenizer
-from transformers.utils import logging, PaddingStrategy
-from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
-
-
-class SPTokenizer:
-    def __init__(self, model_path: str):
-        # reload tokenizer
-        assert os.path.isfile(model_path), model_path
-        self.sp_model = SentencePieceProcessor(model_file=model_path)
-
-        # BOS / EOS token IDs
-        self.n_words: int = self.sp_model.vocab_size()
-        self.bos_id: int = self.sp_model.bos_id()
-        self.eos_id: int = self.sp_model.eos_id()
-        self.pad_id: int = self.sp_model.unk_id()
-        assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()
-
-        role_special_tokens = ["<|system|>", "<|user|>", "<|assistant|>", "<|observation|>"]
-        special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "sop", "eop"] + role_special_tokens
-        self.special_tokens = {}
-        self.index_special_tokens = {}
-        for token in special_tokens:
-            self.special_tokens[token] = self.n_words
-            self.index_special_tokens[self.n_words] = token
-            self.n_words += 1
-        self.role_special_token_expression = "|".join([re.escape(token) for token in role_special_tokens])
-
-    def tokenize(self, s: str, encode_special_tokens=False):
-        if encode_special_tokens:
-            last_index = 0
-            t = []
-            for match in re.finditer(self.role_special_token_expression, s):
-                if last_index < match.start():
-                    t.extend(self.sp_model.EncodeAsPieces(s[last_index:match.start()]))
-                t.append(s[match.start():match.end()])
-                last_index = match.end()
-            if last_index < len(s):
-                t.extend(self.sp_model.EncodeAsPieces(s[last_index:]))
-            return t
-        else:
-            return self.sp_model.EncodeAsPieces(s)
-
-    def encode(self, s: str, bos: bool = False, eos: bool = False) -> List[int]:
-        assert type(s) is str
-        t = self.sp_model.encode(s)
-        if bos:
-            t = [self.bos_id] + t
-        if eos:
-            t = t + [self.eos_id]
-        return t
-
-    def decode(self, t: List[int]) -> str:
-        text, buffer = "", []
-        for token in t:
-            if token in self.index_special_tokens:
-                if buffer:
-                    text += self.sp_model.decode(buffer)
-                    buffer = []
-                text += self.index_special_tokens[token]
-            else:
-                buffer.append(token)
-        if buffer:
-            text += self.sp_model.decode(buffer)
-        return text
-
-    def decode_tokens(self, tokens: List[str]) -> str:
-        text = self.sp_model.DecodePieces(tokens)
-        return text
-
-    def convert_token_to_id(self, token):
-        """ Converts a token (str) in an id using the vocab. """
-        if token in self.special_tokens:
-            return self.special_tokens[token]
-        return self.sp_model.PieceToId(token)
-
-    def convert_id_to_token(self, index):
-        """Converts an index (integer) in a token (str) using the vocab."""
-        if index in self.index_special_tokens:
-            return self.index_special_tokens[index]
-        if index in [self.eos_id, self.bos_id, self.pad_id] or index < 0:
-            return ""
-        return self.sp_model.IdToPiece(index)
-
-
-class ChatGLMTokenizer(PreTrainedTokenizer):
-    vocab_files_names = {"vocab_file": "tokenizer.model"}
-
-    model_input_names = ["input_ids", "attention_mask", "position_ids"]
-
-    def __init__(self, vocab_file, padding_side="left", clean_up_tokenization_spaces=False, encode_special_tokens=False,
-                 **kwargs):
-        self.name = "GLMTokenizer"
-
-        self.vocab_file = vocab_file
-        self.tokenizer = SPTokenizer(vocab_file)
-        self.special_tokens = {
-            "<bos>": self.tokenizer.bos_id,
-            "<eos>": self.tokenizer.eos_id,
-            "<pad>": self.tokenizer.pad_id
-        }
-        self.encode_special_tokens = encode_special_tokens
-        super().__init__(padding_side=padding_side, clean_up_tokenization_spaces=clean_up_tokenization_spaces,
-                         encode_special_tokens=encode_special_tokens,
-                         **kwargs)
-
-    def get_command(self, token):
-        if token in self.special_tokens:
-            return self.special_tokens[token]
-        assert token in self.tokenizer.special_tokens, f"{token} is not a special token for {self.name}"
-        return self.tokenizer.special_tokens[token]
-
-    @property
-    def unk_token(self) -> str:
-        return "<unk>"
-
-    @property
-    def pad_token(self) -> str:
-        return "<unk>"
-
-    @property
-    def pad_token_id(self):
-        return self.get_command("<pad>")
-
-    @property
-    def eos_token(self) -> str:
-        return "</s>"
-
-    @property
-    def eos_token_id(self):
-        return self.get_command("<eos>")
-
-    @property
-    def vocab_size(self):
-        return self.tokenizer.n_words
-
-    def get_vocab(self):
-        """ Returns vocab as a dict """
-        vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
-        vocab.update(self.added_tokens_encoder)
-        return vocab
-
-    def _tokenize(self, text, **kwargs):
-        return self.tokenizer.tokenize(text, encode_special_tokens=self.encode_special_tokens)
-
-    def _convert_token_to_id(self, token):
-        """ Converts a token (str) in an id using the vocab. """
-        return self.tokenizer.convert_token_to_id(token)
-
-    def _convert_id_to_token(self, index):
-        """Converts an index (integer) in a token (str) using the vocab."""
-        return self.tokenizer.convert_id_to_token(index)
-
-    def convert_tokens_to_string(self, tokens: List[str]) -> str:
-        return self.tokenizer.decode_tokens(tokens)
-
-    def save_vocabulary(self, save_directory, filename_prefix=None):
-        """
-        Save the vocabulary and special tokens file to a directory.
-
-        Args:
-            save_directory (`str`):
-                The directory in which to save the vocabulary.
-            filename_prefix (`str`, *optional*):
-                An optional prefix to add to the named of the saved files.
-
-        Returns:
-            `Tuple(str)`: Paths to the files saved.
-        """
-        if os.path.isdir(save_directory):
-            vocab_file = os.path.join(
-                save_directory, self.vocab_files_names["vocab_file"]
-            )
-        else:
-            vocab_file = save_directory
-
-        with open(self.vocab_file, 'rb') as fin:
-            proto_str = fin.read()
-
-        with open(vocab_file, "wb") as writer:
-            writer.write(proto_str)
-
-        return (vocab_file,)
-
-    def get_prefix_tokens(self):
-        prefix_tokens = [self.get_command("[gMASK]"), self.get_command("sop")]
-        return prefix_tokens
-
-    def build_single_message(self, role, metadata, message):
-        assert role in ["system", "user", "assistant", "observation"], role
-        role_tokens = [self.get_command(f"<|{role}|>")] + self.tokenizer.encode(f"{metadata}\n")
-        message_tokens = self.tokenizer.encode(message)
-        tokens = role_tokens + message_tokens
-        return tokens
-
-    def build_chat_input(self, query, history=None, role="user"):
-        if history is None:
-            history = []
-        input_ids = []
-        for item in history:
-            content = item["content"]
-            if item["role"] == "system" and "tools" in item:
-                content = content + "\n" + json.dumps(item["tools"], indent=4, ensure_ascii=False)
-            input_ids.extend(self.build_single_message(item["role"], item.get("metadata", ""), content))
-        input_ids.extend(self.build_single_message(role, "", query))
-        input_ids.extend([self.get_command("<|assistant|>")])
-        return self.batch_encode_plus([input_ids], return_tensors="pt", is_split_into_words=True)
-
-    def build_inputs_with_special_tokens(
-            self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
-    ) -> List[int]:
-        """
-        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
-        adding special tokens. A BERT sequence has the following format:
-
-        - single sequence: `[CLS] X [SEP]`
-        - pair of sequences: `[CLS] A [SEP] B [SEP]`
-
-        Args:
-            token_ids_0 (`List[int]`):
-                List of IDs to which the special tokens will be added.
-            token_ids_1 (`List[int]`, *optional*):
-                Optional second list of IDs for sequence pairs.
-
-        Returns:
-            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
-        """
-        prefix_tokens = self.get_prefix_tokens()
-        token_ids_0 = prefix_tokens + token_ids_0
-        if token_ids_1 is not None:
-            token_ids_0 = token_ids_0 + token_ids_1 + [self.get_command("<eos>")]
-        return token_ids_0
-
-    def _pad(
-            self,
-            encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
-            max_length: Optional[int] = None,
-            padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
-            pad_to_multiple_of: Optional[int] = None,
-            return_attention_mask: Optional[bool] = None,
-    ) -> dict:
-        """
-        Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
-
-        Args:
-            encoded_inputs:
-                Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
-            max_length: maximum length of the returned list and optionally padding length (see below).
-                Will truncate by taking into account the special tokens.
-            padding_strategy: PaddingStrategy to use for padding.
-
-                - PaddingStrategy.LONGEST Pad to the longest sequence in the batch
-                - PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
-                - PaddingStrategy.DO_NOT_PAD: Do not pad
-                The tokenizer padding sides are defined in self.padding_side:
-
-                    - 'left': pads on the left of the sequences
-                    - 'right': pads on the right of the sequences
-            pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
-                This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
-                `>= 7.5` (Volta).
-            return_attention_mask:
-                (optional) Set to False to avoid returning attention mask (default: set to model specifics)
-        """
-        # Load from model defaults
-        assert self.padding_side == "left"
-
-        required_input = encoded_inputs[self.model_input_names[0]]
-        seq_length = len(required_input)
-
-        if padding_strategy == PaddingStrategy.LONGEST:
-            max_length = len(required_input)
-
-        if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
-            max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
-
-        needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
-
-        # Initialize attention mask if not present.
-        if "attention_mask" not in encoded_inputs:
-            encoded_inputs["attention_mask"] = [1] * seq_length
-
-        if "position_ids" not in encoded_inputs:
-            encoded_inputs["position_ids"] = list(range(seq_length))
-
-        if needs_to_be_padded:
-            difference = max_length - len(required_input)
-
-            if "attention_mask" in encoded_inputs:
-                encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
-            if "position_ids" in encoded_inputs:
-                encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
-            encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
-
-        return encoded_inputs

kolors/models/unet_2d_condition.py

@@ -1,1318 +0,0 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional, Tuple, Union
-
-import torch
-import torch.nn as nn
-import torch.utils.checkpoint
-
-from diffusers.configuration_utils import ConfigMixin, register_to_config
-from diffusers.loaders import PeftAdapterMixin, UNet2DConditionLoadersMixin
-from diffusers.loaders.single_file_model import FromOriginalModelMixin
-from diffusers.utils import USE_PEFT_BACKEND, BaseOutput, deprecate, logging, scale_lora_layers, unscale_lora_layers
-from diffusers.models.activations import get_activation
-from diffusers.models.attention_processor import (
-    ADDED_KV_ATTENTION_PROCESSORS,
-    CROSS_ATTENTION_PROCESSORS,
-    Attention,
-    AttentionProcessor,
-    AttnAddedKVProcessor,
-    AttnProcessor,
-)
-from diffusers.models.embeddings import (
-    GaussianFourierProjection,
-    GLIGENTextBoundingboxProjection,
-    ImageHintTimeEmbedding,
-    ImageProjection,
-    ImageTimeEmbedding,
-    TextImageProjection,
-    TextImageTimeEmbedding,
-    TextTimeEmbedding,
-    TimestepEmbedding,
-    Timesteps,
-)
-from diffusers.models.modeling_utils import ModelMixin
-
-try:
-    from diffusers.models.unet_2d_blocks import (
-        get_down_block,
-        get_mid_block,
-        get_up_block,
-    )
-except:
-    from diffusers.models.unets.unet_2d_blocks import (
-        get_down_block,
-        get_mid_block,
-        get_up_block,
-    )
-
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-@dataclass
-class UNet2DConditionOutput(BaseOutput):
-    """
-    The output of [`UNet2DConditionModel`].
-
-    Args:
-        sample (`torch.Tensor` of shape `(batch_size, num_channels, height, width)`):
-            The hidden states output conditioned on `encoder_hidden_states` input. Output of last layer of model.
-    """
-
-    sample: torch.Tensor = None
-
-
-class UNet2DConditionModel(
-    ModelMixin, ConfigMixin, FromOriginalModelMixin, UNet2DConditionLoadersMixin, PeftAdapterMixin
-):
-    r"""
-    A conditional 2D UNet model that takes a noisy sample, conditional state, and a timestep and returns a sample
-    shaped output.
-
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
-    for all models (such as downloading or saving).
-
-    Parameters:
-        sample_size (`int` or `Tuple[int, int]`, *optional*, defaults to `None`):
-            Height and width of input/output sample.
-        in_channels (`int`, *optional*, defaults to 4): Number of channels in the input sample.
-        out_channels (`int`, *optional*, defaults to 4): Number of channels in the output.
-        center_input_sample (`bool`, *optional*, defaults to `False`): Whether to center the input sample.
-        flip_sin_to_cos (`bool`, *optional*, defaults to `True`):
-            Whether to flip the sin to cos in the time embedding.
-        freq_shift (`int`, *optional*, defaults to 0): The frequency shift to apply to the time embedding.
-        down_block_types (`Tuple[str]`, *optional*, defaults to `("CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "DownBlock2D")`):
-            The tuple of downsample blocks to use.
-        mid_block_type (`str`, *optional*, defaults to `"UNetMidBlock2DCrossAttn"`):
-            Block type for middle of UNet, it can be one of `UNetMidBlock2DCrossAttn`, `UNetMidBlock2D`, or
-            `UNetMidBlock2DSimpleCrossAttn`. If `None`, the mid block layer is skipped.
-        up_block_types (`Tuple[str]`, *optional*, defaults to `("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D")`):
-            The tuple of upsample blocks to use.
-        only_cross_attention(`bool` or `Tuple[bool]`, *optional*, default to `False`):
-            Whether to include self-attention in the basic transformer blocks, see
-            [`~models.attention.BasicTransformerBlock`].
-        block_out_channels (`Tuple[int]`, *optional*, defaults to `(320, 640, 1280, 1280)`):
-            The tuple of output channels for each block.
-        layers_per_block (`int`, *optional*, defaults to 2): The number of layers per block.
-        downsample_padding (`int`, *optional*, defaults to 1): The padding to use for the downsampling convolution.
-        mid_block_scale_factor (`float`, *optional*, defaults to 1.0): The scale factor to use for the mid block.
-        dropout (`float`, *optional*, defaults to 0.0): The dropout probability to use.
-        act_fn (`str`, *optional*, defaults to `"silu"`): The activation function to use.
-        norm_num_groups (`int`, *optional*, defaults to 32): The number of groups to use for the normalization.
-            If `None`, normalization and activation layers is skipped in post-processing.
-        norm_eps (`float`, *optional*, defaults to 1e-5): The epsilon to use for the normalization.
-        cross_attention_dim (`int` or `Tuple[int]`, *optional*, defaults to 1280):
-            The dimension of the cross attention features.
-        transformer_layers_per_block (`int`, `Tuple[int]`, or `Tuple[Tuple]` , *optional*, defaults to 1):
-            The number of transformer blocks of type [`~models.attention.BasicTransformerBlock`]. Only relevant for
-            [`~models.unets.unet_2d_blocks.CrossAttnDownBlock2D`], [`~models.unets.unet_2d_blocks.CrossAttnUpBlock2D`],
-            [`~models.unets.unet_2d_blocks.UNetMidBlock2DCrossAttn`].
-        reverse_transformer_layers_per_block : (`Tuple[Tuple]`, *optional*, defaults to None):
-            The number of transformer blocks of type [`~models.attention.BasicTransformerBlock`], in the upsampling
-            blocks of the U-Net. Only relevant if `transformer_layers_per_block` is of type `Tuple[Tuple]` and for
-            [`~models.unets.unet_2d_blocks.CrossAttnDownBlock2D`], [`~models.unets.unet_2d_blocks.CrossAttnUpBlock2D`],
-            [`~models.unets.unet_2d_blocks.UNetMidBlock2DCrossAttn`].
-        encoder_hid_dim (`int`, *optional*, defaults to None):
-            If `encoder_hid_dim_type` is defined, `encoder_hidden_states` will be projected from `encoder_hid_dim`
-            dimension to `cross_attention_dim`.
-        encoder_hid_dim_type (`str`, *optional*, defaults to `None`):
-            If given, the `encoder_hidden_states` and potentially other embeddings are down-projected to text
-            embeddings of dimension `cross_attention` according to `encoder_hid_dim_type`.
-        attention_head_dim (`int`, *optional*, defaults to 8): The dimension of the attention heads.
-        num_attention_heads (`int`, *optional*):
-            The number of attention heads. If not defined, defaults to `attention_head_dim`
-        resnet_time_scale_shift (`str`, *optional*, defaults to `"default"`): Time scale shift config
-            for ResNet blocks (see [`~models.resnet.ResnetBlock2D`]). Choose from `default` or `scale_shift`.
-        class_embed_type (`str`, *optional*, defaults to `None`):
-            The type of class embedding to use which is ultimately summed with the time embeddings. Choose from `None`,
-            `"timestep"`, `"identity"`, `"projection"`, or `"simple_projection"`.
-        addition_embed_type (`str`, *optional*, defaults to `None`):
-            Configures an optional embedding which will be summed with the time embeddings. Choose from `None` or
-            "text". "text" will use the `TextTimeEmbedding` layer.
-        addition_time_embed_dim: (`int`, *optional*, defaults to `None`):
-            Dimension for the timestep embeddings.
-        num_class_embeds (`int`, *optional*, defaults to `None`):
-            Input dimension of the learnable embedding matrix to be projected to `time_embed_dim`, when performing
-            class conditioning with `class_embed_type` equal to `None`.
-        time_embedding_type (`str`, *optional*, defaults to `positional`):
-            The type of position embedding to use for timesteps. Choose from `positional` or `fourier`.
-        time_embedding_dim (`int`, *optional*, defaults to `None`):
-            An optional override for the dimension of the projected time embedding.
-        time_embedding_act_fn (`str`, *optional*, defaults to `None`):
-            Optional activation function to use only once on the time embeddings before they are passed to the rest of
-            the UNet. Choose from `silu`, `mish`, `gelu`, and `swish`.
-        timestep_post_act (`str`, *optional*, defaults to `None`):
-            The second activation function to use in timestep embedding. Choose from `silu`, `mish` and `gelu`.
-        time_cond_proj_dim (`int`, *optional*, defaults to `None`):
-            The dimension of `cond_proj` layer in the timestep embedding.
-        conv_in_kernel (`int`, *optional*, default to `3`): The kernel size of `conv_in` layer.
-        conv_out_kernel (`int`, *optional*, default to `3`): The kernel size of `conv_out` layer.
-        projection_class_embeddings_input_dim (`int`, *optional*): The dimension of the `class_labels` input when
-            `class_embed_type="projection"`. Required when `class_embed_type="projection"`.
-        class_embeddings_concat (`bool`, *optional*, defaults to `False`): Whether to concatenate the time
-            embeddings with the class embeddings.
-        mid_block_only_cross_attention (`bool`, *optional*, defaults to `None`):
-            Whether to use cross attention with the mid block when using the `UNetMidBlock2DSimpleCrossAttn`. If
-            `only_cross_attention` is given as a single boolean and `mid_block_only_cross_attention` is `None`, the
-            `only_cross_attention` value is used as the value for `mid_block_only_cross_attention`. Default to `False`
-            otherwise.
-    """
-
-    _supports_gradient_checkpointing = True
-    _no_split_modules = ["BasicTransformerBlock", "ResnetBlock2D", "CrossAttnUpBlock2D"]
-
-    @register_to_config
-    def __init__(
-        self,
-        sample_size: Optional[int] = None,
-        in_channels: int = 4,
-        out_channels: int = 4,
-        center_input_sample: bool = False,
-        flip_sin_to_cos: bool = True,
-        freq_shift: int = 0,
-        down_block_types: Tuple[str] = (
-            "CrossAttnDownBlock2D",
-            "CrossAttnDownBlock2D",
-            "CrossAttnDownBlock2D",
-            "DownBlock2D",
-        ),
-        mid_block_type: Optional[str] = "UNetMidBlock2DCrossAttn",
-        up_block_types: Tuple[str] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
-        only_cross_attention: Union[bool, Tuple[bool]] = False,
-        block_out_channels: Tuple[int] = (320, 640, 1280, 1280),
-        layers_per_block: Union[int, Tuple[int]] = 2,
-        downsample_padding: int = 1,
-        mid_block_scale_factor: float = 1,
-        dropout: float = 0.0,
-        act_fn: str = "silu",
-        norm_num_groups: Optional[int] = 32,
-        norm_eps: float = 1e-5,
-        cross_attention_dim: Union[int, Tuple[int]] = 1280,
-        transformer_layers_per_block: Union[int, Tuple[int], Tuple[Tuple]] = 1,
-        reverse_transformer_layers_per_block: Optional[Tuple[Tuple[int]]] = None,
-        encoder_hid_dim: Optional[int] = None,
-        encoder_hid_dim_type: Optional[str] = None,
-        attention_head_dim: Union[int, Tuple[int]] = 8,
-        num_attention_heads: Optional[Union[int, Tuple[int]]] = None,
-        dual_cross_attention: bool = False,
-        use_linear_projection: bool = False,
-        class_embed_type: Optional[str] = None,
-        addition_embed_type: Optional[str] = None,
-        addition_time_embed_dim: Optional[int] = None,
-        num_class_embeds: Optional[int] = None,
-        upcast_attention: bool = False,
-        resnet_time_scale_shift: str = "default",
-        resnet_skip_time_act: bool = False,
-        resnet_out_scale_factor: float = 1.0,
-        time_embedding_type: str = "positional",
-        time_embedding_dim: Optional[int] = None,
-        time_embedding_act_fn: Optional[str] = None,
-        timestep_post_act: Optional[str] = None,
-        time_cond_proj_dim: Optional[int] = None,
-        conv_in_kernel: int = 3,
-        conv_out_kernel: int = 3,
-        projection_class_embeddings_input_dim: Optional[int] = None,
-        attention_type: str = "default",
-        class_embeddings_concat: bool = False,
-        mid_block_only_cross_attention: Optional[bool] = None,
-        cross_attention_norm: Optional[str] = None,
-        addition_embed_type_num_heads: int = 64,
-    ):
-        super().__init__()
-
-        self.sample_size = sample_size
-
-        if num_attention_heads is not None:
-            raise ValueError(
-                "At the moment it is not possible to define the number of attention heads via `num_attention_heads` because of a naming issue as described in https://github.com/huggingface/diffusers/issues/2011#issuecomment-1547958131. Passing `num_attention_heads` will only be supported in diffusers v0.19."
-            )
-
-        # If `num_attention_heads` is not defined (which is the case for most models)
-        # it will default to `attention_head_dim`. This looks weird upon first reading it and it is.
-        # The reason for this behavior is to correct for incorrectly named variables that were introduced
-        # when this library was created. The incorrect naming was only discovered much later in https://github.com/huggingface/diffusers/issues/2011#issuecomment-1547958131
-        # Changing `attention_head_dim` to `num_attention_heads` for 40,000+ configurations is too backwards breaking
-        # which is why we correct for the naming here.
-        num_attention_heads = num_attention_heads or attention_head_dim
-
-        # Check inputs
-        self._check_config(
-            down_block_types=down_block_types,
-            up_block_types=up_block_types,
-            only_cross_attention=only_cross_attention,
-            block_out_channels=block_out_channels,
-            layers_per_block=layers_per_block,
-            cross_attention_dim=cross_attention_dim,
-            transformer_layers_per_block=transformer_layers_per_block,
-            reverse_transformer_layers_per_block=reverse_transformer_layers_per_block,
-            attention_head_dim=attention_head_dim,
-            num_attention_heads=num_attention_heads,
-        )
-
-        # input
-        conv_in_padding = (conv_in_kernel - 1) // 2
-        self.conv_in = nn.Conv2d(
-            in_channels, block_out_channels[0], kernel_size=conv_in_kernel, padding=conv_in_padding
-        )
-
-        # time
-        time_embed_dim, timestep_input_dim = self._set_time_proj(
-            time_embedding_type,
-            block_out_channels=block_out_channels,
-            flip_sin_to_cos=flip_sin_to_cos,
-            freq_shift=freq_shift,
-            time_embedding_dim=time_embedding_dim,
-        )
-
-        self.time_embedding = TimestepEmbedding(
-            timestep_input_dim,
-            time_embed_dim,
-            act_fn=act_fn,
-            post_act_fn=timestep_post_act,
-            cond_proj_dim=time_cond_proj_dim,
-        )
-
-        self._set_encoder_hid_proj(
-            encoder_hid_dim_type,
-            cross_attention_dim=cross_attention_dim,
-            encoder_hid_dim=encoder_hid_dim,
-        )
-
-        # class embedding
-        self._set_class_embedding(
-            class_embed_type,
-            act_fn=act_fn,
-            num_class_embeds=num_class_embeds,
-            projection_class_embeddings_input_dim=projection_class_embeddings_input_dim,
-            time_embed_dim=time_embed_dim,
-            timestep_input_dim=timestep_input_dim,
-        )
-
-        self._set_add_embedding(
-            addition_embed_type,
-            addition_embed_type_num_heads=addition_embed_type_num_heads,
-            addition_time_embed_dim=addition_time_embed_dim,
-            cross_attention_dim=cross_attention_dim,
-            encoder_hid_dim=encoder_hid_dim,
-            flip_sin_to_cos=flip_sin_to_cos,
-            freq_shift=freq_shift,
-            projection_class_embeddings_input_dim=projection_class_embeddings_input_dim,
-            time_embed_dim=time_embed_dim,
-        )
-
-        if time_embedding_act_fn is None:
-            self.time_embed_act = None
-        else:
-            self.time_embed_act = get_activation(time_embedding_act_fn)
-
-        self.down_blocks = nn.ModuleList([])
-        self.up_blocks = nn.ModuleList([])
-
-        if isinstance(only_cross_attention, bool):
-            if mid_block_only_cross_attention is None:
-                mid_block_only_cross_attention = only_cross_attention
-
-            only_cross_attention = [only_cross_attention] * len(down_block_types)
-
-        if mid_block_only_cross_attention is None:
-            mid_block_only_cross_attention = False
-
-        if isinstance(num_attention_heads, int):
-            num_attention_heads = (num_attention_heads,) * len(down_block_types)
-
-        if isinstance(attention_head_dim, int):
-            attention_head_dim = (attention_head_dim,) * len(down_block_types)
-
-        if isinstance(cross_attention_dim, int):
-            cross_attention_dim = (cross_attention_dim,) * len(down_block_types)
-
-        if isinstance(layers_per_block, int):
-            layers_per_block = [layers_per_block] * len(down_block_types)
-
-        if isinstance(transformer_layers_per_block, int):
-            transformer_layers_per_block = [transformer_layers_per_block] * len(down_block_types)
-
-        if class_embeddings_concat:
-            # The time embeddings are concatenated with the class embeddings. The dimension of the
-            # time embeddings passed to the down, middle, and up blocks is twice the dimension of the
-            # regular time embeddings
-            blocks_time_embed_dim = time_embed_dim * 2
-        else:
-            blocks_time_embed_dim = time_embed_dim
-
-        # down
-        output_channel = block_out_channels[0]
-        for i, down_block_type in enumerate(down_block_types):
-            input_channel = output_channel
-            output_channel = block_out_channels[i]
-            is_final_block = i == len(block_out_channels) - 1
-
-            down_block = get_down_block(
-                down_block_type,
-                num_layers=layers_per_block[i],
-                transformer_layers_per_block=transformer_layers_per_block[i],
-                in_channels=input_channel,
-                out_channels=output_channel,
-                temb_channels=blocks_time_embed_dim,
-                add_downsample=not is_final_block,
-                resnet_eps=norm_eps,
-                resnet_act_fn=act_fn,
-                resnet_groups=norm_num_groups,
-                cross_attention_dim=cross_attention_dim[i],
-                num_attention_heads=num_attention_heads[i],
-                downsample_padding=downsample_padding,
-                dual_cross_attention=dual_cross_attention,
-                use_linear_projection=use_linear_projection,
-                only_cross_attention=only_cross_attention[i],
-                upcast_attention=upcast_attention,
-                resnet_time_scale_shift=resnet_time_scale_shift,
-                attention_type=attention_type,
-                resnet_skip_time_act=resnet_skip_time_act,
-                resnet_out_scale_factor=resnet_out_scale_factor,
-                cross_attention_norm=cross_attention_norm,
-                attention_head_dim=attention_head_dim[i] if attention_head_dim[i] is not None else output_channel,
-                dropout=dropout,
-            )
-            self.down_blocks.append(down_block)
-
-        # mid
-        self.mid_block = get_mid_block(
-            mid_block_type,
-            temb_channels=blocks_time_embed_dim,
-            in_channels=block_out_channels[-1],
-            resnet_eps=norm_eps,
-            resnet_act_fn=act_fn,
-            resnet_groups=norm_num_groups,
-            output_scale_factor=mid_block_scale_factor,
-            transformer_layers_per_block=transformer_layers_per_block[-1],
-            num_attention_heads=num_attention_heads[-1],
-            cross_attention_dim=cross_attention_dim[-1],
-            dual_cross_attention=dual_cross_attention,
-            use_linear_projection=use_linear_projection,
-            mid_block_only_cross_attention=mid_block_only_cross_attention,
-            upcast_attention=upcast_attention,
-            resnet_time_scale_shift=resnet_time_scale_shift,
-            attention_type=attention_type,
-            resnet_skip_time_act=resnet_skip_time_act,
-            cross_attention_norm=cross_attention_norm,
-            attention_head_dim=attention_head_dim[-1],
-            dropout=dropout,
-        )
-
-        # count how many layers upsample the images
-        self.num_upsamplers = 0
-
-        # up
-        reversed_block_out_channels = list(reversed(block_out_channels))
-        reversed_num_attention_heads = list(reversed(num_attention_heads))
-        reversed_layers_per_block = list(reversed(layers_per_block))
-        reversed_cross_attention_dim = list(reversed(cross_attention_dim))
-        reversed_transformer_layers_per_block = (
-            list(reversed(transformer_layers_per_block))
-            if reverse_transformer_layers_per_block is None
-            else reverse_transformer_layers_per_block
-        )
-        only_cross_attention = list(reversed(only_cross_attention))
-
-        output_channel = reversed_block_out_channels[0]
-        for i, up_block_type in enumerate(up_block_types):
-            is_final_block = i == len(block_out_channels) - 1
-
-            prev_output_channel = output_channel
-            output_channel = reversed_block_out_channels[i]
-            input_channel = reversed_block_out_channels[min(i + 1, len(block_out_channels) - 1)]
-
-            # add upsample block for all BUT final layer
-            if not is_final_block:
-                add_upsample = True
-                self.num_upsamplers += 1
-            else:
-                add_upsample = False
-
-            up_block = get_up_block(
-                up_block_type,
-                num_layers=reversed_layers_per_block[i] + 1,
-                transformer_layers_per_block=reversed_transformer_layers_per_block[i],
-                in_channels=input_channel,
-                out_channels=output_channel,
-                prev_output_channel=prev_output_channel,
-                temb_channels=blocks_time_embed_dim,
-                add_upsample=add_upsample,
-                resnet_eps=norm_eps,
-                resnet_act_fn=act_fn,
-                resolution_idx=i,
-                resnet_groups=norm_num_groups,
-                cross_attention_dim=reversed_cross_attention_dim[i],
-                num_attention_heads=reversed_num_attention_heads[i],
-                dual_cross_attention=dual_cross_attention,
-                use_linear_projection=use_linear_projection,
-                only_cross_attention=only_cross_attention[i],
-                upcast_attention=upcast_attention,
-                resnet_time_scale_shift=resnet_time_scale_shift,
-                attention_type=attention_type,
-                resnet_skip_time_act=resnet_skip_time_act,
-                resnet_out_scale_factor=resnet_out_scale_factor,
-                cross_attention_norm=cross_attention_norm,
-                attention_head_dim=attention_head_dim[i] if attention_head_dim[i] is not None else output_channel,
-                dropout=dropout,
-            )
-            self.up_blocks.append(up_block)
-            prev_output_channel = output_channel
-
-        # out
-        if norm_num_groups is not None:
-            self.conv_norm_out = nn.GroupNorm(
-                num_channels=block_out_channels[0], num_groups=norm_num_groups, eps=norm_eps
-            )
-
-            self.conv_act = get_activation(act_fn)
-
-        else:
-            self.conv_norm_out = None
-            self.conv_act = None
-
-        conv_out_padding = (conv_out_kernel - 1) // 2
-        self.conv_out = nn.Conv2d(
-            block_out_channels[0], out_channels, kernel_size=conv_out_kernel, padding=conv_out_padding
-        )
-
-        self._set_pos_net_if_use_gligen(attention_type=attention_type, cross_attention_dim=cross_attention_dim)
-
-    def _check_config(
-        self,
-        down_block_types: Tuple[str],
-        up_block_types: Tuple[str],
-        only_cross_attention: Union[bool, Tuple[bool]],
-        block_out_channels: Tuple[int],
-        layers_per_block: Union[int, Tuple[int]],
-        cross_attention_dim: Union[int, Tuple[int]],
-        transformer_layers_per_block: Union[int, Tuple[int], Tuple[Tuple[int]]],
-        reverse_transformer_layers_per_block: bool,
-        attention_head_dim: int,
-        num_attention_heads: Optional[Union[int, Tuple[int]]],
-    ):
-        if len(down_block_types) != len(up_block_types):
-            raise ValueError(
-                f"Must provide the same number of `down_block_types` as `up_block_types`. `down_block_types`: {down_block_types}. `up_block_types`: {up_block_types}."
-            )
-
-        if len(block_out_channels) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `block_out_channels` as `down_block_types`. `block_out_channels`: {block_out_channels}. `down_block_types`: {down_block_types}."
-            )
-
-        if not isinstance(only_cross_attention, bool) and len(only_cross_attention) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `only_cross_attention` as `down_block_types`. `only_cross_attention`: {only_cross_attention}. `down_block_types`: {down_block_types}."
-            )
-
-        if not isinstance(num_attention_heads, int) and len(num_attention_heads) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `num_attention_heads` as `down_block_types`. `num_attention_heads`: {num_attention_heads}. `down_block_types`: {down_block_types}."
-            )
-
-        if not isinstance(attention_head_dim, int) and len(attention_head_dim) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `attention_head_dim` as `down_block_types`. `attention_head_dim`: {attention_head_dim}. `down_block_types`: {down_block_types}."
-            )
-
-        if isinstance(cross_attention_dim, list) and len(cross_attention_dim) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `cross_attention_dim` as `down_block_types`. `cross_attention_dim`: {cross_attention_dim}. `down_block_types`: {down_block_types}."
-            )
-
-        if not isinstance(layers_per_block, int) and len(layers_per_block) != len(down_block_types):
-            raise ValueError(
-                f"Must provide the same number of `layers_per_block` as `down_block_types`. `layers_per_block`: {layers_per_block}. `down_block_types`: {down_block_types}."
-            )
-        if isinstance(transformer_layers_per_block, list) and reverse_transformer_layers_per_block is None:
-            for layer_number_per_block in transformer_layers_per_block:
-                if isinstance(layer_number_per_block, list):
-                    raise ValueError("Must provide 'reverse_transformer_layers_per_block` if using asymmetrical UNet.")
-
-    def _set_time_proj(
-        self,
-        time_embedding_type: str,
-        block_out_channels: int,
-        flip_sin_to_cos: bool,
-        freq_shift: float,
-        time_embedding_dim: int,
-    ) -> Tuple[int, int]:
-        if time_embedding_type == "fourier":
-            time_embed_dim = time_embedding_dim or block_out_channels[0] * 2
-            if time_embed_dim % 2 != 0:
-                raise ValueError(f"`time_embed_dim` should be divisible by 2, but is {time_embed_dim}.")
-            self.time_proj = GaussianFourierProjection(
-                time_embed_dim // 2, set_W_to_weight=False, log=False, flip_sin_to_cos=flip_sin_to_cos
-            )
-            timestep_input_dim = time_embed_dim
-        elif time_embedding_type == "positional":
-            time_embed_dim = time_embedding_dim or block_out_channels[0] * 4
-
-            self.time_proj = Timesteps(block_out_channels[0], flip_sin_to_cos, freq_shift)
-            timestep_input_dim = block_out_channels[0]
-        else:
-            raise ValueError(
-                f"{time_embedding_type} does not exist. Please make sure to use one of `fourier` or `positional`."
-            )
-
-        return time_embed_dim, timestep_input_dim
-
-    def _set_encoder_hid_proj(
-        self,
-        encoder_hid_dim_type: Optional[str],
-        cross_attention_dim: Union[int, Tuple[int]],
-        encoder_hid_dim: Optional[int],
-    ):
-        if encoder_hid_dim_type is None and encoder_hid_dim is not None:
-            encoder_hid_dim_type = "text_proj"
-            self.register_to_config(encoder_hid_dim_type=encoder_hid_dim_type)
-            logger.info("encoder_hid_dim_type defaults to 'text_proj' as `encoder_hid_dim` is defined.")
-
-        if encoder_hid_dim is None and encoder_hid_dim_type is not None:
-            raise ValueError(
-                f"`encoder_hid_dim` has to be defined when `encoder_hid_dim_type` is set to {encoder_hid_dim_type}."
-            )
-
-        if encoder_hid_dim_type == "text_proj":
-            self.encoder_hid_proj = nn.Linear(encoder_hid_dim, cross_attention_dim)
-        elif encoder_hid_dim_type == "text_image_proj":
-            # image_embed_dim DOESN'T have to be `cross_attention_dim`. To not clutter the __init__ too much
-            # they are set to `cross_attention_dim` here as this is exactly the required dimension for the currently only use
-            # case when `addition_embed_type == "text_image_proj"` (Kandinsky 2.1)`
-            self.encoder_hid_proj = TextImageProjection(
-                text_embed_dim=encoder_hid_dim,
-                image_embed_dim=cross_attention_dim,
-                cross_attention_dim=cross_attention_dim,
-            )
-        elif encoder_hid_dim_type == "image_proj":
-            # Kandinsky 2.2
-            self.encoder_hid_proj = ImageProjection(
-                image_embed_dim=encoder_hid_dim,
-                cross_attention_dim=cross_attention_dim,
-            )
-        elif encoder_hid_dim_type is not None:
-            raise ValueError(
-                f"encoder_hid_dim_type: {encoder_hid_dim_type} must be None, 'text_proj' or 'text_image_proj'."
-            )
-        else:
-            self.encoder_hid_proj = None
-
-    def _set_class_embedding(
-        self,
-        class_embed_type: Optional[str],
-        act_fn: str,
-        num_class_embeds: Optional[int],
-        projection_class_embeddings_input_dim: Optional[int],
-        time_embed_dim: int,
-        timestep_input_dim: int,
-    ):
-        if class_embed_type is None and num_class_embeds is not None:
-            self.class_embedding = nn.Embedding(num_class_embeds, time_embed_dim)
-        elif class_embed_type == "timestep":
-            self.class_embedding = TimestepEmbedding(timestep_input_dim, time_embed_dim, act_fn=act_fn)
-        elif class_embed_type == "identity":
-            self.class_embedding = nn.Identity(time_embed_dim, time_embed_dim)
-        elif class_embed_type == "projection":
-            if projection_class_embeddings_input_dim is None:
-                raise ValueError(
-                    "`class_embed_type`: 'projection' requires `projection_class_embeddings_input_dim` be set"
-                )
-            # The projection `class_embed_type` is the same as the timestep `class_embed_type` except
-            # 1. the `class_labels` inputs are not first converted to sinusoidal embeddings
-            # 2. it projects from an arbitrary input dimension.
-            #
-            # Note that `TimestepEmbedding` is quite general, being mainly linear layers and activations.
-            # When used for embedding actual timesteps, the timesteps are first converted to sinusoidal embeddings.
-            # As a result, `TimestepEmbedding` can be passed arbitrary vectors.
-            self.class_embedding = TimestepEmbedding(projection_class_embeddings_input_dim, time_embed_dim)
-        elif class_embed_type == "simple_projection":
-            if projection_class_embeddings_input_dim is None:
-                raise ValueError(
-                    "`class_embed_type`: 'simple_projection' requires `projection_class_embeddings_input_dim` be set"
-                )
-            self.class_embedding = nn.Linear(projection_class_embeddings_input_dim, time_embed_dim)
-        else:
-            self.class_embedding = None
-
-    def _set_add_embedding(
-        self,
-        addition_embed_type: str,
-        addition_embed_type_num_heads: int,
-        addition_time_embed_dim: Optional[int],
-        flip_sin_to_cos: bool,
-        freq_shift: float,
-        cross_attention_dim: Optional[int],
-        encoder_hid_dim: Optional[int],
-        projection_class_embeddings_input_dim: Optional[int],
-        time_embed_dim: int,
-    ):
-        if addition_embed_type == "text":
-            if encoder_hid_dim is not None:
-                text_time_embedding_from_dim = encoder_hid_dim
-            else:
-                text_time_embedding_from_dim = cross_attention_dim
-
-            self.add_embedding = TextTimeEmbedding(
-                text_time_embedding_from_dim, time_embed_dim, num_heads=addition_embed_type_num_heads
-            )
-        elif addition_embed_type == "text_image":
-            # text_embed_dim and image_embed_dim DON'T have to be `cross_attention_dim`. To not clutter the __init__ too much
-            # they are set to `cross_attention_dim` here as this is exactly the required dimension for the currently only use
-            # case when `addition_embed_type == "text_image"` (Kandinsky 2.1)`
-            self.add_embedding = TextImageTimeEmbedding(
-                text_embed_dim=cross_attention_dim, image_embed_dim=cross_attention_dim, time_embed_dim=time_embed_dim
-            )
-        elif addition_embed_type == "text_time":
-            self.add_time_proj = Timesteps(addition_time_embed_dim, flip_sin_to_cos, freq_shift)
-            self.add_embedding = TimestepEmbedding(projection_class_embeddings_input_dim, time_embed_dim)
-        elif addition_embed_type == "image":
-            # Kandinsky 2.2
-            self.add_embedding = ImageTimeEmbedding(image_embed_dim=encoder_hid_dim, time_embed_dim=time_embed_dim)
-        elif addition_embed_type == "image_hint":
-            # Kandinsky 2.2 ControlNet
-            self.add_embedding = ImageHintTimeEmbedding(image_embed_dim=encoder_hid_dim, time_embed_dim=time_embed_dim)
-        elif addition_embed_type is not None:
-            raise ValueError(f"addition_embed_type: {addition_embed_type} must be None, 'text' or 'text_image'.")
-
-    def _set_pos_net_if_use_gligen(self, attention_type: str, cross_attention_dim: int):
-        if attention_type in ["gated", "gated-text-image"]:
-            positive_len = 768
-            if isinstance(cross_attention_dim, int):
-                positive_len = cross_attention_dim
-            elif isinstance(cross_attention_dim, (list, tuple)):
-                positive_len = cross_attention_dim[0]
-
-            feature_type = "text-only" if attention_type == "gated" else "text-image"
-            self.position_net = GLIGENTextBoundingboxProjection(
-                positive_len=positive_len, out_dim=cross_attention_dim, feature_type=feature_type
-            )
-
-    @property
-    def attn_processors(self) -> Dict[str, AttentionProcessor]:
-        r"""
-        Returns:
-            `dict` of attention processors: A dictionary containing all attention processors used in the model with
-            indexed by its weight name.
-        """
-        # set recursively
-        processors = {}
-
-        def fn_recursive_add_processors(name: str, module: torch.nn.Module, processors: Dict[str, AttentionProcessor]):
-            if hasattr(module, "get_processor"):
-                processors[f"{name}.processor"] = module.get_processor()
-
-            for sub_name, child in module.named_children():
-                fn_recursive_add_processors(f"{name}.{sub_name}", child, processors)
-
-            return processors
-
-        for name, module in self.named_children():
-            fn_recursive_add_processors(name, module, processors)
-
-        return processors
-
-    def set_attn_processor(self, processor: Union[AttentionProcessor, Dict[str, AttentionProcessor]]):
-        r"""
-        Sets the attention processor to use to compute attention.
-
-        Parameters:
-            processor (`dict` of `AttentionProcessor` or only `AttentionProcessor`):
-                The instantiated processor class or a dictionary of processor classes that will be set as the processor
-                for **all** `Attention` layers.
-
-                If `processor` is a dict, the key needs to define the path to the corresponding cross attention
-                processor. This is strongly recommended when setting trainable attention processors.
-
-        """
-        count = len(self.attn_processors.keys())
-
-        if isinstance(processor, dict) and len(processor) != count:
-            raise ValueError(
-                f"A dict of processors was passed, but the number of processors {len(processor)} does not match the"
-                f" number of attention layers: {count}. Please make sure to pass {count} processor classes."
-            )
-
-        def fn_recursive_attn_processor(name: str, module: torch.nn.Module, processor):
-            if hasattr(module, "set_processor"):
-                if not isinstance(processor, dict):
-                    module.set_processor(processor)
-                else:
-                    module.set_processor(processor.pop(f"{name}.processor"))
-
-            for sub_name, child in module.named_children():
-                fn_recursive_attn_processor(f"{name}.{sub_name}", child, processor)
-
-        for name, module in self.named_children():
-            fn_recursive_attn_processor(name, module, processor)
-
-    def set_default_attn_processor(self):
-        """
-        Disables custom attention processors and sets the default attention implementation.
-        """
-        if all(proc.__class__ in ADDED_KV_ATTENTION_PROCESSORS for proc in self.attn_processors.values()):
-            processor = AttnAddedKVProcessor()
-        elif all(proc.__class__ in CROSS_ATTENTION_PROCESSORS for proc in self.attn_processors.values()):
-            processor = AttnProcessor()
-        else:
-            raise ValueError(
-                f"Cannot call `set_default_attn_processor` when attention processors are of type {next(iter(self.attn_processors.values()))}"
-            )
-
-        self.set_attn_processor(processor)
-
-    def set_attention_slice(self, slice_size: Union[str, int, List[int]] = "auto"):
-        r"""
-        Enable sliced attention computation.
-
-        When this option is enabled, the attention module splits the input tensor in slices to compute attention in
-        several steps. This is useful for saving some memory in exchange for a small decrease in speed.
-
-        Args:
-            slice_size (`str` or `int` or `list(int)`, *optional*, defaults to `"auto"`):
-                When `"auto"`, input to the attention heads is halved, so attention is computed in two steps. If
-                `"max"`, maximum amount of memory is saved by running only one slice at a time. If a number is
-                provided, uses as many slices as `attention_head_dim // slice_size`. In this case, `attention_head_dim`
-                must be a multiple of `slice_size`.
-        """
-        sliceable_head_dims = []
-
-        def fn_recursive_retrieve_sliceable_dims(module: torch.nn.Module):
-            if hasattr(module, "set_attention_slice"):
-                sliceable_head_dims.append(module.sliceable_head_dim)
-
-            for child in module.children():
-                fn_recursive_retrieve_sliceable_dims(child)
-
-        # retrieve number of attention layers
-        for module in self.children():
-            fn_recursive_retrieve_sliceable_dims(module)
-
-        num_sliceable_layers = len(sliceable_head_dims)
-
-        if slice_size == "auto":
-            # half the attention head size is usually a good trade-off between
-            # speed and memory
-            slice_size = [dim // 2 for dim in sliceable_head_dims]
-        elif slice_size == "max":
-            # make smallest slice possible
-            slice_size = num_sliceable_layers * [1]
-
-        slice_size = num_sliceable_layers * [slice_size] if not isinstance(slice_size, list) else slice_size
-
-        if len(slice_size) != len(sliceable_head_dims):
-            raise ValueError(
-                f"You have provided {len(slice_size)}, but {self.config} has {len(sliceable_head_dims)} different"
-                f" attention layers. Make sure to match `len(slice_size)` to be {len(sliceable_head_dims)}."
-            )
-
-        for i in range(len(slice_size)):
-            size = slice_size[i]
-            dim = sliceable_head_dims[i]
-            if size is not None and size > dim:
-                raise ValueError(f"size {size} has to be smaller or equal to {dim}.")
-
-        # Recursively walk through all the children.
-        # Any children which exposes the set_attention_slice method
-        # gets the message
-        def fn_recursive_set_attention_slice(module: torch.nn.Module, slice_size: List[int]):
-            if hasattr(module, "set_attention_slice"):
-                module.set_attention_slice(slice_size.pop())
-
-            for child in module.children():
-                fn_recursive_set_attention_slice(child, slice_size)
-
-        reversed_slice_size = list(reversed(slice_size))
-        for module in self.children():
-            fn_recursive_set_attention_slice(module, reversed_slice_size)
-
-    def _set_gradient_checkpointing(self, module, value=False):
-        if hasattr(module, "gradient_checkpointing"):
-            module.gradient_checkpointing = value
-
-    def enable_freeu(self, s1: float, s2: float, b1: float, b2: float):
-        r"""Enables the FreeU mechanism from https://arxiv.org/abs/2309.11497.
-
-        The suffixes after the scaling factors represent the stage blocks where they are being applied.
-
-        Please refer to the [official repository](https://github.com/ChenyangSi/FreeU) for combinations of values that
-        are known to work well for different pipelines such as Stable Diffusion v1, v2, and Stable Diffusion XL.
-
-        Args:
-            s1 (`float`):
-                Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to
-                mitigate the "oversmoothing effect" in the enhanced denoising process.
-            s2 (`float`):
-                Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to
-                mitigate the "oversmoothing effect" in the enhanced denoising process.
-            b1 (`float`): Scaling factor for stage 1 to amplify the contributions of backbone features.
-            b2 (`float`): Scaling factor for stage 2 to amplify the contributions of backbone features.
-        """
-        for i, upsample_block in enumerate(self.up_blocks):
-            setattr(upsample_block, "s1", s1)
-            setattr(upsample_block, "s2", s2)
-            setattr(upsample_block, "b1", b1)
-            setattr(upsample_block, "b2", b2)
-
-    def disable_freeu(self):
-        """Disables the FreeU mechanism."""
-        freeu_keys = {"s1", "s2", "b1", "b2"}
-        for i, upsample_block in enumerate(self.up_blocks):
-            for k in freeu_keys:
-                if hasattr(upsample_block, k) or getattr(upsample_block, k, None) is not None:
-                    setattr(upsample_block, k, None)
-
-    def fuse_qkv_projections(self):
-        """
-        Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value)
-        are fused. For cross-attention modules, key and value projection matrices are fused.
-
-        <Tip warning={true}>
-
-        This API is 🧪 experimental.
-
-        </Tip>
-        """
-        self.original_attn_processors = None
-
-        for _, attn_processor in self.attn_processors.items():
-            if "Added" in str(attn_processor.__class__.__name__):
-                raise ValueError("`fuse_qkv_projections()` is not supported for models having added KV projections.")
-
-        self.original_attn_processors = self.attn_processors
-
-        for module in self.modules():
-            if isinstance(module, Attention):
-                module.fuse_projections(fuse=True)
-
-    def unfuse_qkv_projections(self):
-        """Disables the fused QKV projection if enabled.
-
-        <Tip warning={true}>
-
-        This API is 🧪 experimental.
-
-        </Tip>
-
-        """
-        if self.original_attn_processors is not None:
-            self.set_attn_processor(self.original_attn_processors)
-
-    def get_time_embed(
-        self, sample: torch.Tensor, timestep: Union[torch.Tensor, float, int]
-    ) -> Optional[torch.Tensor]:
-        timesteps = timestep
-        if not torch.is_tensor(timesteps):
-            # TODO: this requires sync between CPU and GPU. So try to pass timesteps as tensors if you can
-            # This would be a good case for the `match` statement (Python 3.10+)
-            is_mps = sample.device.type == "mps"
-            if isinstance(timestep, float):
-                dtype = torch.float32 if is_mps else torch.float64
-            else:
-                dtype = torch.int32 if is_mps else torch.int64
-            timesteps = torch.tensor([timesteps], dtype=dtype, device=sample.device)
-        elif len(timesteps.shape) == 0:
-            timesteps = timesteps[None].to(sample.device)
-
-        # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
-        timesteps = timesteps.expand(sample.shape[0])
-
-        t_emb = self.time_proj(timesteps)
-        # `Timesteps` does not contain any weights and will always return f32 tensors
-        # but time_embedding might actually be running in fp16. so we need to cast here.
-        # there might be better ways to encapsulate this.
-        t_emb = t_emb.to(dtype=sample.dtype)
-        return t_emb
-
-    def get_class_embed(self, sample: torch.Tensor, class_labels: Optional[torch.Tensor]) -> Optional[torch.Tensor]:
-        class_emb = None
-        if self.class_embedding is not None:
-            if class_labels is None:
-                raise ValueError("class_labels should be provided when num_class_embeds > 0")
-
-            if self.config.class_embed_type == "timestep":
-                class_labels = self.time_proj(class_labels)
-
-                # `Timesteps` does not contain any weights and will always return f32 tensors
-                # there might be better ways to encapsulate this.
-                class_labels = class_labels.to(dtype=sample.dtype)
-
-            class_emb = self.class_embedding(class_labels).to(dtype=sample.dtype)
-        return class_emb
-
-    def get_aug_embed(
-        self, emb: torch.Tensor, encoder_hidden_states: torch.Tensor, added_cond_kwargs: Dict[str, Any]
-    ) -> Optional[torch.Tensor]:
-        aug_emb = None
-        if self.config.addition_embed_type == "text":
-            aug_emb = self.add_embedding(encoder_hidden_states)
-        elif self.config.addition_embed_type == "text_image":
-            # Kandinsky 2.1 - style
-            if "image_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `addition_embed_type` set to 'text_image' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`"
-                )
-
-            image_embs = added_cond_kwargs.get("image_embeds")
-            text_embs = added_cond_kwargs.get("text_embeds", encoder_hidden_states)
-            aug_emb = self.add_embedding(text_embs, image_embs)
-        elif self.config.addition_embed_type == "text_time":
-            # SDXL - style
-            if "text_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `text_embeds` to be passed in `added_cond_kwargs`"
-                )
-            text_embeds = added_cond_kwargs.get("text_embeds")
-            if "time_ids" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `time_ids` to be passed in `added_cond_kwargs`"
-                )
-            time_ids = added_cond_kwargs.get("time_ids")
-            time_embeds = self.add_time_proj(time_ids.flatten())
-            time_embeds = time_embeds.reshape((text_embeds.shape[0], -1))
-            add_embeds = torch.concat([text_embeds, time_embeds], dim=-1)
-            add_embeds = add_embeds.to(emb.dtype)
-            aug_emb = self.add_embedding(add_embeds)
-        elif self.config.addition_embed_type == "image":
-            # Kandinsky 2.2 - style
-            if "image_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `addition_embed_type` set to 'image' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`"
-                )
-            image_embs = added_cond_kwargs.get("image_embeds")
-            aug_emb = self.add_embedding(image_embs)
-        elif self.config.addition_embed_type == "image_hint":
-            # Kandinsky 2.2 - style
-            if "image_embeds" not in added_cond_kwargs or "hint" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `addition_embed_type` set to 'image_hint' which requires the keyword arguments `image_embeds` and `hint` to be passed in `added_cond_kwargs`"
-                )
-            image_embs = added_cond_kwargs.get("image_embeds")
-            hint = added_cond_kwargs.get("hint")
-            aug_emb = self.add_embedding(image_embs, hint)
-        return aug_emb
-
-    def process_encoder_hidden_states(
-        self, encoder_hidden_states: torch.Tensor, added_cond_kwargs: Dict[str, Any]
-    ) -> torch.Tensor:
-        if self.encoder_hid_proj is not None and self.config.encoder_hid_dim_type == "text_proj":
-            encoder_hidden_states = self.encoder_hid_proj(encoder_hidden_states)
-        elif self.encoder_hid_proj is not None and self.config.encoder_hid_dim_type == "text_image_proj":
-            # Kandinsky 2.1 - style
-            if "image_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'text_image_proj' which requires the keyword argument `image_embeds` to be passed in  `added_conditions`"
-                )
-
-            image_embeds = added_cond_kwargs.get("image_embeds")
-            encoder_hidden_states = self.encoder_hid_proj(encoder_hidden_states, image_embeds)
-        elif self.encoder_hid_proj is not None and self.config.encoder_hid_dim_type == "image_proj":
-            # Kandinsky 2.2 - style
-            if "image_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'image_proj' which requires the keyword argument `image_embeds` to be passed in  `added_conditions`"
-                )
-            image_embeds = added_cond_kwargs.get("image_embeds")
-            encoder_hidden_states = self.encoder_hid_proj(image_embeds)
-        elif self.encoder_hid_proj is not None and self.config.encoder_hid_dim_type == "ip_image_proj":
-            if "image_embeds" not in added_cond_kwargs:
-                raise ValueError(
-                    f"{self.__class__} has the config param `encoder_hid_dim_type` set to 'ip_image_proj' which requires the keyword argument `image_embeds` to be passed in  `added_conditions`"
-                )
-            
-            if hasattr(self, 'text_encoder_hid_proj') and not self.text_encoder_hid_proj is None:
-                encoder_hidden_states = self.text_encoder_hid_proj( encoder_hidden_states )
-            
-            image_embeds = added_cond_kwargs.get("image_embeds")
-            image_embeds = self.encoder_hid_proj(image_embeds)
-            encoder_hidden_states = (encoder_hidden_states, image_embeds)
-        return encoder_hidden_states
-
-    def forward(
-        self,
-        sample: torch.Tensor,
-        timestep: Union[torch.Tensor, float, int],
-        encoder_hidden_states: torch.Tensor,
-        class_labels: Optional[torch.Tensor] = None,
-        timestep_cond: Optional[torch.Tensor] = None,
-        attention_mask: Optional[torch.Tensor] = None,
-        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-        added_cond_kwargs: Optional[Dict[str, torch.Tensor]] = None,
-        down_block_additional_residuals: Optional[Tuple[torch.Tensor]] = None,
-        mid_block_additional_residual: Optional[torch.Tensor] = None,
-        down_intrablock_additional_residuals: Optional[Tuple[torch.Tensor]] = None,
-        encoder_attention_mask: Optional[torch.Tensor] = None,
-        return_dict: bool = True,
-    ) -> Union[UNet2DConditionOutput, Tuple]:
-        r"""
-        The [`UNet2DConditionModel`] forward method.
-
-        Args:
-            sample (`torch.Tensor`):
-                The noisy input tensor with the following shape `(batch, channel, height, width)`.
-            timestep (`torch.Tensor` or `float` or `int`): The number of timesteps to denoise an input.
-            encoder_hidden_states (`torch.Tensor`):
-                The encoder hidden states with shape `(batch, sequence_length, feature_dim)`.
-            class_labels (`torch.Tensor`, *optional*, defaults to `None`):
-                Optional class labels for conditioning. Their embeddings will be summed with the timestep embeddings.
-            timestep_cond: (`torch.Tensor`, *optional*, defaults to `None`):
-                Conditional embeddings for timestep. If provided, the embeddings will be summed with the samples passed
-                through the `self.time_embedding` layer to obtain the timestep embeddings.
-            attention_mask (`torch.Tensor`, *optional*, defaults to `None`):
-                An attention mask of shape `(batch, key_tokens)` is applied to `encoder_hidden_states`. If `1` the mask
-                is kept, otherwise if `0` it is discarded. Mask will be converted into a bias, which adds large
-                negative values to the attention scores corresponding to "discard" tokens.
-            cross_attention_kwargs (`dict`, *optional*):
-                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
-                `self.processor` in
-                [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
-            added_cond_kwargs: (`dict`, *optional*):
-                A kwargs dictionary containing additional embeddings that if specified are added to the embeddings that
-                are passed along to the UNet blocks.
-            down_block_additional_residuals: (`tuple` of `torch.Tensor`, *optional*):
-                A tuple of tensors that if specified are added to the residuals of down unet blocks.
-            mid_block_additional_residual: (`torch.Tensor`, *optional*):
-                A tensor that if specified is added to the residual of the middle unet block.
-            down_intrablock_additional_residuals (`tuple` of `torch.Tensor`, *optional*):
-                additional residuals to be added within UNet down blocks, for example from T2I-Adapter side model(s)
-            encoder_attention_mask (`torch.Tensor`):
-                A cross-attention mask of shape `(batch, sequence_length)` is applied to `encoder_hidden_states`. If
-                `True` the mask is kept, otherwise if `False` it is discarded. Mask will be converted into a bias,
-                which adds large negative values to the attention scores corresponding to "discard" tokens.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~models.unets.unet_2d_condition.UNet2DConditionOutput`] instead of a plain
-                tuple.
-
-        Returns:
-            [`~models.unets.unet_2d_condition.UNet2DConditionOutput`] or `tuple`:
-                If `return_dict` is True, an [`~models.unets.unet_2d_condition.UNet2DConditionOutput`] is returned,
-                otherwise a `tuple` is returned where the first element is the sample tensor.
-        """
-        # By default samples have to be AT least a multiple of the overall upsampling factor.
-        # The overall upsampling factor is equal to 2 ** (# num of upsampling layers).
-        # However, the upsampling interpolation output size can be forced to fit any upsampling size
-        # on the fly if necessary.
-        default_overall_up_factor = 2**self.num_upsamplers
-
-        # upsample size should be forwarded when sample is not a multiple of `default_overall_up_factor`
-        forward_upsample_size = False
-        upsample_size = None
-
-        for dim in sample.shape[-2:]:
-            if dim % default_overall_up_factor != 0:
-                # Forward upsample size to force interpolation output size.
-                forward_upsample_size = True
-                break
-
-        # ensure attention_mask is a bias, and give it a singleton query_tokens dimension
-        # expects mask of shape:
-        #   [batch, key_tokens]
-        # adds singleton query_tokens dimension:
-        #   [batch,                    1, key_tokens]
-        # this helps to broadcast it as a bias over attention scores, which will be in one of the following shapes:
-        #   [batch,  heads, query_tokens, key_tokens] (e.g. torch sdp attn)
-        #   [batch * heads, query_tokens, key_tokens] (e.g. xformers or classic attn)
-        if attention_mask is not None:
-            # assume that mask is expressed as:
-            #   (1 = keep,      0 = discard)
-            # convert mask into a bias that can be added to attention scores:
-            #       (keep = +0,     discard = -10000.0)
-            attention_mask = (1 - attention_mask.to(sample.dtype)) * -10000.0
-            attention_mask = attention_mask.unsqueeze(1)
-
-        # convert encoder_attention_mask to a bias the same way we do for attention_mask
-        if encoder_attention_mask is not None:
-            encoder_attention_mask = (1 - encoder_attention_mask.to(sample.dtype)) * -10000.0
-            encoder_attention_mask = encoder_attention_mask.unsqueeze(1)
-
-        # 0. center input if necessary
-        if self.config.center_input_sample:
-            sample = 2 * sample - 1.0
-
-        # 1. time
-        t_emb = self.get_time_embed(sample=sample, timestep=timestep)
-        emb = self.time_embedding(t_emb, timestep_cond)
-        aug_emb = None
-
-        class_emb = self.get_class_embed(sample=sample, class_labels=class_labels)
-        if class_emb is not None:
-            if self.config.class_embeddings_concat:
-                emb = torch.cat([emb, class_emb], dim=-1)
-            else:
-                emb = emb + class_emb
-
-        aug_emb = self.get_aug_embed(
-            emb=emb, encoder_hidden_states=encoder_hidden_states, added_cond_kwargs=added_cond_kwargs
-        )
-        if self.config.addition_embed_type == "image_hint":
-            aug_emb, hint = aug_emb
-            sample = torch.cat([sample, hint], dim=1)
-
-        emb = emb + aug_emb if aug_emb is not None else emb
-
-        if self.time_embed_act is not None:
-            emb = self.time_embed_act(emb)
-
-        encoder_hidden_states = self.process_encoder_hidden_states(
-            encoder_hidden_states=encoder_hidden_states, added_cond_kwargs=added_cond_kwargs
-        )
-
-        # 2. pre-process
-        sample = self.conv_in(sample)
-
-        # 2.5 GLIGEN position net
-        if cross_attention_kwargs is not None and cross_attention_kwargs.get("gligen", None) is not None:
-            cross_attention_kwargs = cross_attention_kwargs.copy()
-            gligen_args = cross_attention_kwargs.pop("gligen")
-            cross_attention_kwargs["gligen"] = {"objs": self.position_net(**gligen_args)}
-
-        # 3. down
-        # we're popping the `scale` instead of getting it because otherwise `scale` will be propagated
-        # to the internal blocks and will raise deprecation warnings. this will be confusing for our users.
-        if cross_attention_kwargs is not None:
-            cross_attention_kwargs = cross_attention_kwargs.copy()
-            lora_scale = cross_attention_kwargs.pop("scale", 1.0)
-        else:
-            lora_scale = 1.0
-
-        if USE_PEFT_BACKEND:
-            # weight the lora layers by setting `lora_scale` for each PEFT layer
-            scale_lora_layers(self, lora_scale)
-
-        is_controlnet = mid_block_additional_residual is not None and down_block_additional_residuals is not None
-        # using new arg down_intrablock_additional_residuals for T2I-Adapters, to distinguish from controlnets
-        is_adapter = down_intrablock_additional_residuals is not None
-        # maintain backward compatibility for legacy usage, where
-        #       T2I-Adapter and ControlNet both use down_block_additional_residuals arg
-        #       but can only use one or the other
-        if not is_adapter and mid_block_additional_residual is None and down_block_additional_residuals is not None:
-            deprecate(
-                "T2I should not use down_block_additional_residuals",
-                "1.3.0",
-                "Passing intrablock residual connections with `down_block_additional_residuals` is deprecated \
-                       and will be removed in diffusers 1.3.0.  `down_block_additional_residuals` should only be used \
-                       for ControlNet. Please make sure use `down_intrablock_additional_residuals` instead. ",
-                standard_warn=False,
-            )
-            down_intrablock_additional_residuals = down_block_additional_residuals
-            is_adapter = True
-
-        down_block_res_samples = (sample,)
-        for downsample_block in self.down_blocks:
-            if hasattr(downsample_block, "has_cross_attention") and downsample_block.has_cross_attention:
-                # For t2i-adapter CrossAttnDownBlock2D
-                additional_residuals = {}
-                if is_adapter and len(down_intrablock_additional_residuals) > 0:
-                    additional_residuals["additional_residuals"] = down_intrablock_additional_residuals.pop(0)
-
-                sample, res_samples = downsample_block(
-                    hidden_states=sample,
-                    temb=emb,
-                    encoder_hidden_states=encoder_hidden_states,
-                    attention_mask=attention_mask,
-                    cross_attention_kwargs=cross_attention_kwargs,
-                    encoder_attention_mask=encoder_attention_mask,
-                    **additional_residuals,
-                )
-            else:
-                sample, res_samples = downsample_block(hidden_states=sample, temb=emb)
-                if is_adapter and len(down_intrablock_additional_residuals) > 0:
-                    sample += down_intrablock_additional_residuals.pop(0)
-
-            down_block_res_samples += res_samples
-
-        if is_controlnet:
-            new_down_block_res_samples = ()
-
-            for down_block_res_sample, down_block_additional_residual in zip(
-                down_block_res_samples, down_block_additional_residuals
-            ):
-                down_block_res_sample = down_block_res_sample + down_block_additional_residual
-                new_down_block_res_samples = new_down_block_res_samples + (down_block_res_sample,)
-
-            down_block_res_samples = new_down_block_res_samples
-
-        # 4. mid
-        if self.mid_block is not None:
-            if hasattr(self.mid_block, "has_cross_attention") and self.mid_block.has_cross_attention:
-                sample = self.mid_block(
-                    sample,
-                    emb,
-                    encoder_hidden_states=encoder_hidden_states,
-                    attention_mask=attention_mask,
-                    cross_attention_kwargs=cross_attention_kwargs,
-                    encoder_attention_mask=encoder_attention_mask,
-                )
-            else:
-                sample = self.mid_block(sample, emb)
-
-            # To support T2I-Adapter-XL
-            if (
-                is_adapter
-                and len(down_intrablock_additional_residuals) > 0
-                and sample.shape == down_intrablock_additional_residuals[0].shape
-            ):
-                sample += down_intrablock_additional_residuals.pop(0)
-
-        if is_controlnet:
-            sample = sample + mid_block_additional_residual
-
-        # 5. up
-        for i, upsample_block in enumerate(self.up_blocks):
-            is_final_block = i == len(self.up_blocks) - 1
-
-            res_samples = down_block_res_samples[-len(upsample_block.resnets) :]
-            down_block_res_samples = down_block_res_samples[: -len(upsample_block.resnets)]
-
-            # if we have not reached the final block and need to forward the
-            # upsample size, we do it here
-            if not is_final_block and forward_upsample_size:
-                upsample_size = down_block_res_samples[-1].shape[2:]
-
-            if hasattr(upsample_block, "has_cross_attention") and upsample_block.has_cross_attention:
-                sample = upsample_block(
-                    hidden_states=sample,
-                    temb=emb,
-                    res_hidden_states_tuple=res_samples,
-                    encoder_hidden_states=encoder_hidden_states,
-                    cross_attention_kwargs=cross_attention_kwargs,
-                    upsample_size=upsample_size,
-                    attention_mask=attention_mask,
-                    encoder_attention_mask=encoder_attention_mask,
-                )
-            else:
-                sample = upsample_block(
-                    hidden_states=sample,
-                    temb=emb,
-                    res_hidden_states_tuple=res_samples,
-                    upsample_size=upsample_size,
-                )
-
-        # 6. post-process
-        if self.conv_norm_out:
-            sample = self.conv_norm_out(sample)
-            sample = self.conv_act(sample)
-        sample = self.conv_out(sample)
-
-        if USE_PEFT_BACKEND:
-            # remove `lora_scale` from each PEFT layer
-            unscale_lora_layers(self, lora_scale)
-
-        if not return_dict:
-            return (sample,)
-
-        return UNet2DConditionOutput(sample=sample)

kolors/pipelines/pipeline_controlnet_xl_kolors_img2img.py

@@ -1,1365 +0,0 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-
-import inspect
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
-
-import numpy as np
-import PIL.Image
-import torch
-import torch.nn.functional as F
-from transformers import (
-    CLIPImageProcessor,
-    CLIPTextModel,
-    CLIPTextModelWithProjection,
-    CLIPTokenizer,
-    CLIPVisionModelWithProjection,
-)
-
-from diffusers.utils.import_utils import is_invisible_watermark_available
-
-from diffusers.callbacks import MultiPipelineCallbacks, PipelineCallback
-from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
-from diffusers.loaders import (
-    FromSingleFileMixin,
-    IPAdapterMixin,
-    StableDiffusionXLLoraLoaderMixin,
-    TextualInversionLoaderMixin,
-)
-from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    XFormersAttnProcessor,
-)
-from diffusers.models.lora import adjust_lora_scale_text_encoder
-from diffusers.schedulers import KarrasDiffusionSchedulers
-from diffusers.utils import (
-    USE_PEFT_BACKEND,
-    deprecate,
-    logging,
-    replace_example_docstring,
-    scale_lora_layers,
-    unscale_lora_layers,
-)
-from diffusers.utils.torch_utils import is_compiled_module, randn_tensor
-from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
-from diffusers.pipelines.controlnet import MultiControlNetModel
-
-from ..models.controlnet import ControlNetModel
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.retrieve_latents
-def retrieve_latents(
-    encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample"
-):
-    if hasattr(encoder_output, "latent_dist") and sample_mode == "sample":
-        return encoder_output.latent_dist.sample(generator)
-    elif hasattr(encoder_output, "latent_dist") and sample_mode == "argmax":
-        return encoder_output.latent_dist.mode()
-    elif hasattr(encoder_output, "latents"):
-        return encoder_output.latents
-    else:
-        raise AttributeError("Could not access latents of provided encoder_output")
-
-
-class StableDiffusionXLControlNetImg2ImgPipeline(
-    DiffusionPipeline,
-    StableDiffusionMixin,
-    TextualInversionLoaderMixin,
-    StableDiffusionXLLoraLoaderMixin,
-    FromSingleFileMixin,
-    IPAdapterMixin,
-):
-    r"""
-    Pipeline for image-to-image generation using Stable Diffusion XL with ControlNet guidance.
-
-    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
-    library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
-
-    The pipeline also inherits the following loading methods:
-        - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
-        - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
-
-    Args:
-        vae ([`AutoencoderKL`]):
-            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
-        text_encoder ([`CLIPTextModel`]):
-            Frozen text-encoder. Stable Diffusion uses the text portion of
-            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel), specifically
-            the [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) variant.
-        tokenizer (`CLIPTokenizer`):
-            Tokenizer of class
-            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
-        unet ([`UNet2DConditionModel`]): Conditional U-Net architecture to denoise the encoded image latents.
-        controlnet ([`ControlNetModel`] or `List[ControlNetModel]`):
-            Provides additional conditioning to the unet during the denoising process. If you set multiple ControlNets
-            as a list, the outputs from each ControlNet are added together to create one combined additional
-            conditioning.
-        scheduler ([`SchedulerMixin`]):
-            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
-            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
-        requires_aesthetics_score (`bool`, *optional*, defaults to `"False"`):
-            Whether the `unet` requires an `aesthetic_score` condition to be passed during inference. Also see the
-            config of `stabilityai/stable-diffusion-xl-refiner-1-0`.
-        force_zeros_for_empty_prompt (`bool`, *optional*, defaults to `"True"`):
-            Whether the negative prompt embeddings shall be forced to always be set to 0. Also see the config of
-            `stabilityai/stable-diffusion-xl-base-1-0`.
-        add_watermarker (`bool`, *optional*):
-            Whether to use the [invisible_watermark library](https://github.com/ShieldMnt/invisible-watermark/) to
-            watermark output images. If not defined, it will default to True if the package is installed, otherwise no
-            watermarker will be used.
-        feature_extractor ([`~transformers.CLIPImageProcessor`]):
-            A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
-    """
-
-    model_cpu_offload_seq = "text_encoder->image_encoder->unet->vae"
-    _optional_components = [
-        "tokenizer",
-        "text_encoder",
-        "feature_extractor",
-        "image_encoder",
-    ]
-    _callback_tensor_inputs = [
-        "latents",
-        "prompt_embeds",
-        "negative_prompt_embeds",
-        "add_text_embeds",
-        "add_time_ids",
-        "negative_pooled_prompt_embeds",
-        "add_neg_time_ids",
-    ]
-
-    def __init__(
-        self,
-        vae: AutoencoderKL,
-        text_encoder: CLIPTextModel,
-        tokenizer: CLIPTokenizer,
-        unet: UNet2DConditionModel,
-        controlnet: Union[ControlNetModel, List[ControlNetModel], Tuple[ControlNetModel], MultiControlNetModel],
-        scheduler: KarrasDiffusionSchedulers,
-        requires_aesthetics_score: bool = False,
-        force_zeros_for_empty_prompt: bool = True,
-        feature_extractor: CLIPImageProcessor = None,
-        image_encoder: CLIPVisionModelWithProjection = None,
-    ):
-        super().__init__()
-
-        if isinstance(controlnet, (list, tuple)):
-            controlnet = MultiControlNetModel(controlnet)
-
-        self.register_modules(
-            vae=vae,
-            text_encoder=text_encoder,
-            tokenizer=tokenizer,
-            unet=unet,
-            controlnet=controlnet,
-            scheduler=scheduler,
-            feature_extractor=feature_extractor,
-            image_encoder=image_encoder,
-        )
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
-        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor, do_convert_rgb=True)
-        self.control_image_processor = VaeImageProcessor(
-            vae_scale_factor=self.vae_scale_factor, do_convert_rgb=True, do_normalize=False
-        )
-
-        self.watermark = None
-
-        self.register_to_config(force_zeros_for_empty_prompt=force_zeros_for_empty_prompt)
-        self.register_to_config(requires_aesthetics_score=requires_aesthetics_score)
-
-
-    def encode_prompt(
-        self,
-        prompt,
-        device: Optional[torch.device] = None,
-        num_images_per_prompt: int = 1,
-        do_classifier_free_guidance: bool = True,
-        negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        lora_scale: Optional[float] = None,
-    ):
-        r"""
-        Encodes the prompt into text encoder hidden states.
-
-        Args:
-             prompt (`str` or `List[str]`, *optional*):
-                prompt to be encoded
-            device: (`torch.device`):
-                torch device
-            num_images_per_prompt (`int`):
-                number of images that should be generated per prompt
-            do_classifier_free_guidance (`bool`):
-                whether to use classifier free guidance or not
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
-                If not provided, pooled text embeddings will be generated from `prompt` input argument.
-            negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
-                input argument.
-            lora_scale (`float`, *optional*):
-                A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
-        """
-        # from IPython import embed; embed(); exit()
-        device = device or self._execution_device
-
-        # set lora scale so that monkey patched LoRA
-        # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
-            self._lora_scale = lora_scale
-
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        # Define tokenizers and text encoders
-        tokenizers = [self.tokenizer]
-        text_encoders = [self.text_encoder]
-
-        if prompt_embeds is None:
-            # textual inversion: procecss multi-vector tokens if necessary
-            prompt_embeds_list = []
-            for tokenizer, text_encoder in zip(tokenizers, text_encoders):
-                if isinstance(self, TextualInversionLoaderMixin):
-                    prompt = self.maybe_convert_prompt(prompt, tokenizer)
-
-                text_inputs = tokenizer(
-                    prompt,
-                    padding="max_length",
-                    max_length=256,
-                    truncation=True,
-                    return_tensors="pt",
-                ).to('cuda')
-                output = text_encoder(
-                        input_ids=text_inputs['input_ids'] ,
-                        attention_mask=text_inputs['attention_mask'],
-                        position_ids=text_inputs['position_ids'],
-                        output_hidden_states=True)
-                prompt_embeds = output.hidden_states[-2].permute(1, 0, 2).clone()
-                pooled_prompt_embeds = output.hidden_states[-1][-1, :, :].clone() # [batch_size, 4096]
-                bs_embed, seq_len, _ = prompt_embeds.shape
-                prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
-                prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)
-
-                prompt_embeds_list.append(prompt_embeds)
-
-            # prompt_embeds = torch.concat(prompt_embeds_list, dim=-1)
-            prompt_embeds = prompt_embeds_list[0]
-
-        # get unconditional embeddings for classifier free guidance
-        zero_out_negative_prompt = negative_prompt is None and self.config.force_zeros_for_empty_prompt
-        if do_classifier_free_guidance and negative_prompt_embeds is None and zero_out_negative_prompt:
-            negative_prompt_embeds = torch.zeros_like(prompt_embeds)
-            negative_pooled_prompt_embeds = torch.zeros_like(pooled_prompt_embeds)
-        elif do_classifier_free_guidance and negative_prompt_embeds is None:
-            # negative_prompt = negative_prompt or ""
-            uncond_tokens: List[str]
-            if negative_prompt is None:
-                uncond_tokens = [""] * batch_size
-            elif prompt is not None and type(prompt) is not type(negative_prompt):
-                raise TypeError(
-                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
-                    f" {type(prompt)}."
-                )
-            elif isinstance(negative_prompt, str):
-                uncond_tokens = [negative_prompt]
-            elif batch_size != len(negative_prompt):
-                raise ValueError(
-                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
-                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
-                    " the batch size of `prompt`."
-                )
-            else:
-                uncond_tokens = negative_prompt
-
-            negative_prompt_embeds_list = []
-            for tokenizer, text_encoder in zip(tokenizers, text_encoders):
-                # textual inversion: procecss multi-vector tokens if necessary
-                if isinstance(self, TextualInversionLoaderMixin):
-                    uncond_tokens = self.maybe_convert_prompt(uncond_tokens, tokenizer)
-
-                max_length = prompt_embeds.shape[1]
-                uncond_input = tokenizer(
-                    uncond_tokens,
-                    padding="max_length",
-                    max_length=max_length,
-                    truncation=True,
-                    return_tensors="pt",
-                ).to('cuda')
-                output = text_encoder(
-                        input_ids=uncond_input['input_ids'] ,
-                        attention_mask=uncond_input['attention_mask'],
-                        position_ids=uncond_input['position_ids'],
-                        output_hidden_states=True)
-                negative_prompt_embeds = output.hidden_states[-2].permute(1, 0, 2).clone()
-                negative_pooled_prompt_embeds = output.hidden_states[-1][-1, :, :].clone() # [batch_size, 4096]
-
-                if do_classifier_free_guidance:
-                    # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
-                    seq_len = negative_prompt_embeds.shape[1]
-
-                    negative_prompt_embeds = negative_prompt_embeds.to(dtype=text_encoder.dtype, device=device)
-
-                    negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
-                    negative_prompt_embeds = negative_prompt_embeds.view(
-                        batch_size * num_images_per_prompt, seq_len, -1
-                    )
-
-                    # For classifier free guidance, we need to do two forward passes.
-                    # Here we concatenate the unconditional and text embeddings into a single batch
-                    # to avoid doing two forward passes
-
-                negative_prompt_embeds_list.append(negative_prompt_embeds)
-
-            # negative_prompt_embeds = torch.concat(negative_prompt_embeds_list, dim=-1)
-            negative_prompt_embeds = negative_prompt_embeds_list[0]
-
-        bs_embed = pooled_prompt_embeds.shape[0]
-        pooled_prompt_embeds = pooled_prompt_embeds.repeat(1, num_images_per_prompt).view(
-            bs_embed * num_images_per_prompt, -1
-        )
-        if do_classifier_free_guidance:
-            negative_pooled_prompt_embeds = negative_pooled_prompt_embeds.repeat(1, num_images_per_prompt).view(
-                bs_embed * num_images_per_prompt, -1
-            )
-
-        return prompt_embeds, negative_prompt_embeds, pooled_prompt_embeds, negative_pooled_prompt_embeds
-
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
-    def encode_image(self, image, device, num_images_per_prompt, output_hidden_states=None):
-        dtype = next(self.image_encoder.parameters()).dtype
-
-        if not isinstance(image, torch.Tensor):
-            image = self.feature_extractor(image, return_tensors="pt").pixel_values
-
-        image = image.to(device=device, dtype=dtype)
-        if output_hidden_states:
-            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True).hidden_states[-2]
-            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
-            uncond_image_enc_hidden_states = self.image_encoder(
-                torch.zeros_like(image), output_hidden_states=True
-            ).hidden_states[-2]
-            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
-                num_images_per_prompt, dim=0
-            )
-            return image_enc_hidden_states, uncond_image_enc_hidden_states
-        else:
-            image_embeds = self.image_encoder(image).image_embeds
-            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
-            uncond_image_embeds = torch.zeros_like(image_embeds)
-
-            return image_embeds, uncond_image_embeds
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_ip_adapter_image_embeds
-    def prepare_ip_adapter_image_embeds(
-        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
-    ):
-        image_embeds = []
-        if do_classifier_free_guidance:
-            negative_image_embeds = []
-        if ip_adapter_image_embeds is None:
-            if not isinstance(ip_adapter_image, list):
-                ip_adapter_image = [ip_adapter_image]
-
-            if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
-                raise ValueError(
-                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP Adapters."
-                )
-
-            for single_ip_adapter_image, image_proj_layer in zip(
-                ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
-            ):
-                output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
-                single_image_embeds, single_negative_image_embeds = self.encode_image(
-                    single_ip_adapter_image, device, 1, output_hidden_state
-                )
-
-                image_embeds.append(single_image_embeds[None, :])
-                if do_classifier_free_guidance:
-                    negative_image_embeds.append(single_negative_image_embeds[None, :])
-        else:
-            for single_image_embeds in ip_adapter_image_embeds:
-                if do_classifier_free_guidance:
-                    single_negative_image_embeds, single_image_embeds = single_image_embeds.chunk(2)
-                    negative_image_embeds.append(single_negative_image_embeds)
-                image_embeds.append(single_image_embeds)
-
-        ip_adapter_image_embeds = []
-        for i, single_image_embeds in enumerate(image_embeds):
-            single_image_embeds = torch.cat([single_image_embeds] * num_images_per_prompt, dim=0)
-            if do_classifier_free_guidance:
-                single_negative_image_embeds = torch.cat([negative_image_embeds[i]] * num_images_per_prompt, dim=0)
-                single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds], dim=0)
-
-            single_image_embeds = single_image_embeds.to(device=device)
-            ip_adapter_image_embeds.append(single_image_embeds)
-
-        return ip_adapter_image_embeds
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
-    def prepare_extra_step_kwargs(self, generator, eta):
-        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
-        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
-        # and should be between [0, 1]
-
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        # check if the scheduler accepts generator
-        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        if accepts_generator:
-            extra_step_kwargs["generator"] = generator
-        return extra_step_kwargs
-
-    def check_inputs(
-        self,
-        prompt,
-        image,
-        strength,
-        num_inference_steps,
-        callback_steps,
-        negative_prompt=None,
-        prompt_embeds=None,
-        negative_prompt_embeds=None,
-        pooled_prompt_embeds=None,
-        negative_pooled_prompt_embeds=None,
-        ip_adapter_image=None,
-        ip_adapter_image_embeds=None,
-        controlnet_conditioning_scale=1.0,
-        control_guidance_start=0.0,
-        control_guidance_end=1.0,
-        callback_on_step_end_tensor_inputs=None,
-    ):
-        if strength < 0 or strength > 1:
-            raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")
-        if num_inference_steps is None:
-            raise ValueError("`num_inference_steps` cannot be None.")
-        elif not isinstance(num_inference_steps, int) or num_inference_steps <= 0:
-            raise ValueError(
-                f"`num_inference_steps` has to be a positive integer but is {num_inference_steps} of type"
-                f" {type(num_inference_steps)}."
-            )
-
-        if callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0):
-            raise ValueError(
-                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
-                f" {type(callback_steps)}."
-            )
-
-        if callback_on_step_end_tensor_inputs is not None and not all(
-            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
-        ):
-            raise ValueError(
-                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"
-            )
-
-        if prompt is not None and prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
-                " only forward one of the two."
-            )
-        elif prompt is None and prompt_embeds is None:
-            raise ValueError(
-                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
-            )
-        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
-            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
-
-        if negative_prompt is not None and negative_prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
-                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
-            )
-
-        if prompt_embeds is not None and negative_prompt_embeds is not None:
-            if prompt_embeds.shape != negative_prompt_embeds.shape:
-                raise ValueError(
-                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
-                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
-                    f" {negative_prompt_embeds.shape}."
-                )
-
-        if prompt_embeds is not None and pooled_prompt_embeds is None:
-            raise ValueError(
-                "If `prompt_embeds` are provided, `pooled_prompt_embeds` also have to be passed. Make sure to generate `pooled_prompt_embeds` from the same text encoder that was used to generate `prompt_embeds`."
-            )
-
-        if negative_prompt_embeds is not None and negative_pooled_prompt_embeds is None:
-            raise ValueError(
-                "If `negative_prompt_embeds` are provided, `negative_pooled_prompt_embeds` also have to be passed. Make sure to generate `negative_pooled_prompt_embeds` from the same text encoder that was used to generate `negative_prompt_embeds`."
-            )
-
-        # `prompt` needs more sophisticated handling when there are multiple
-        # conditionings.
-        if isinstance(self.controlnet, MultiControlNetModel):
-            if isinstance(prompt, list):
-                logger.warning(
-                    f"You have {len(self.controlnet.nets)} ControlNets and you have passed {len(prompt)}"
-                    " prompts. The conditionings will be fixed across the prompts."
-                )
-
-        # Check `image`
-        is_compiled = hasattr(F, "scaled_dot_product_attention") and isinstance(
-            self.controlnet, torch._dynamo.eval_frame.OptimizedModule
-        )
-        if (
-            isinstance(self.controlnet, ControlNetModel)
-            or is_compiled
-            and isinstance(self.controlnet._orig_mod, ControlNetModel)
-        ):
-            self.check_image(image, prompt, prompt_embeds)
-        elif (
-            isinstance(self.controlnet, MultiControlNetModel)
-            or is_compiled
-            and isinstance(self.controlnet._orig_mod, MultiControlNetModel)
-        ):
-            if not isinstance(image, list):
-                raise TypeError("For multiple controlnets: `image` must be type `list`")
-
-            # When `image` is a nested list:
-            # (e.g. [[canny_image_1, pose_image_1], [canny_image_2, pose_image_2]])
-            elif any(isinstance(i, list) for i in image):
-                raise ValueError("A single batch of multiple conditionings are supported at the moment.")
-            elif len(image) != len(self.controlnet.nets):
-                raise ValueError(
-                    f"For multiple controlnets: `image` must have the same length as the number of controlnets, but got {len(image)} images and {len(self.controlnet.nets)} ControlNets."
-                )
-
-            for image_ in image:
-                self.check_image(image_, prompt, prompt_embeds)
-        else:
-            assert False
-
-        # Check `controlnet_conditioning_scale`
-        if (
-            isinstance(self.controlnet, ControlNetModel)
-            or is_compiled
-            and isinstance(self.controlnet._orig_mod, ControlNetModel)
-        ):
-            if not isinstance(controlnet_conditioning_scale, float):
-                raise TypeError("For single controlnet: `controlnet_conditioning_scale` must be type `float`.")
-        elif (
-            isinstance(self.controlnet, MultiControlNetModel)
-            or is_compiled
-            and isinstance(self.controlnet._orig_mod, MultiControlNetModel)
-        ):
-            if isinstance(controlnet_conditioning_scale, list):
-                if any(isinstance(i, list) for i in controlnet_conditioning_scale):
-                    raise ValueError("A single batch of multiple conditionings are supported at the moment.")
-            elif isinstance(controlnet_conditioning_scale, list) and len(controlnet_conditioning_scale) != len(
-                self.controlnet.nets
-            ):
-                raise ValueError(
-                    "For multiple controlnets: When `controlnet_conditioning_scale` is specified as `list`, it must have"
-                    " the same length as the number of controlnets"
-                )
-        else:
-            assert False
-
-        if not isinstance(control_guidance_start, (tuple, list)):
-            control_guidance_start = [control_guidance_start]
-
-        if not isinstance(control_guidance_end, (tuple, list)):
-            control_guidance_end = [control_guidance_end]
-
-        if len(control_guidance_start) != len(control_guidance_end):
-            raise ValueError(
-                f"`control_guidance_start` has {len(control_guidance_start)} elements, but `control_guidance_end` has {len(control_guidance_end)} elements. Make sure to provide the same number of elements to each list."
-            )
-
-        if isinstance(self.controlnet, MultiControlNetModel):
-            if len(control_guidance_start) != len(self.controlnet.nets):
-                raise ValueError(
-                    f"`control_guidance_start`: {control_guidance_start} has {len(control_guidance_start)} elements but there are {len(self.controlnet.nets)} controlnets available. Make sure to provide {len(self.controlnet.nets)}."
-                )
-
-        for start, end in zip(control_guidance_start, control_guidance_end):
-            if start >= end:
-                raise ValueError(
-                    f"control guidance start: {start} cannot be larger or equal to control guidance end: {end}."
-                )
-            if start < 0.0:
-                raise ValueError(f"control guidance start: {start} can't be smaller than 0.")
-            if end > 1.0:
-                raise ValueError(f"control guidance end: {end} can't be larger than 1.0.")
-
-        if ip_adapter_image is not None and ip_adapter_image_embeds is not None:
-            raise ValueError(
-                "Provide either `ip_adapter_image` or `ip_adapter_image_embeds`. Cannot leave both `ip_adapter_image` and `ip_adapter_image_embeds` defined."
-            )
-
-        if ip_adapter_image_embeds is not None:
-            if not isinstance(ip_adapter_image_embeds, list):
-                raise ValueError(
-                    f"`ip_adapter_image_embeds` has to be of type `list` but is {type(ip_adapter_image_embeds)}"
-                )
-            elif ip_adapter_image_embeds[0].ndim not in [3, 4]:
-                raise ValueError(
-                    f"`ip_adapter_image_embeds` has to be a list of 3D or 4D tensors but is {ip_adapter_image_embeds[0].ndim}D"
-                )
-
-    # Copied from diffusers.pipelines.controlnet.pipeline_controlnet_sd_xl.StableDiffusionXLControlNetPipeline.check_image
-    def check_image(self, image, prompt, prompt_embeds):
-        image_is_pil = isinstance(image, PIL.Image.Image)
-        image_is_tensor = isinstance(image, torch.Tensor)
-        image_is_np = isinstance(image, np.ndarray)
-        image_is_pil_list = isinstance(image, list) and isinstance(image[0], PIL.Image.Image)
-        image_is_tensor_list = isinstance(image, list) and isinstance(image[0], torch.Tensor)
-        image_is_np_list = isinstance(image, list) and isinstance(image[0], np.ndarray)
-
-        if (
-            not image_is_pil
-            and not image_is_tensor
-            and not image_is_np
-            and not image_is_pil_list
-            and not image_is_tensor_list
-            and not image_is_np_list
-        ):
-            raise TypeError(
-                f"image must be passed and be one of PIL image, numpy array, torch tensor, list of PIL images, list of numpy arrays or list of torch tensors, but is {type(image)}"
-            )
-
-        if image_is_pil:
-            image_batch_size = 1
-        else:
-            image_batch_size = len(image)
-
-        if prompt is not None and isinstance(prompt, str):
-            prompt_batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            prompt_batch_size = len(prompt)
-        elif prompt_embeds is not None:
-            prompt_batch_size = prompt_embeds.shape[0]
-
-        if image_batch_size != 1 and image_batch_size != prompt_batch_size:
-            raise ValueError(
-                f"If image batch size is not 1, image batch size must be same as prompt batch size. image batch size: {image_batch_size}, prompt batch size: {prompt_batch_size}"
-            )
-
-    # Copied from diffusers.pipelines.controlnet.pipeline_controlnet_sd_xl.StableDiffusionXLControlNetPipeline.prepare_image
-    def prepare_control_image(
-        self,
-        image,
-        width,
-        height,
-        batch_size,
-        num_images_per_prompt,
-        device,
-        dtype,
-        do_classifier_free_guidance=False,
-        guess_mode=False,
-    ):
-        image = self.control_image_processor.preprocess(image, height=height, width=width).to(dtype=torch.float32)
-        image_batch_size = image.shape[0]
-
-        if image_batch_size == 1:
-            repeat_by = batch_size
-        else:
-            # image batch size is the same as prompt batch size
-            repeat_by = num_images_per_prompt
-
-        image = image.repeat_interleave(repeat_by, dim=0)
-
-        image = image.to(device=device, dtype=dtype)
-
-        if do_classifier_free_guidance and not guess_mode:
-            image = torch.cat([image] * 2)
-
-        return image
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.StableDiffusionImg2ImgPipeline.get_timesteps
-    def get_timesteps(self, num_inference_steps, strength, device):
-        # get the original timestep using init_timestep
-        init_timestep = min(int(num_inference_steps * strength), num_inference_steps)
-
-        t_start = max(num_inference_steps - init_timestep, 0)
-        timesteps = self.scheduler.timesteps[t_start * self.scheduler.order :]
-        if hasattr(self.scheduler, "set_begin_index"):
-            self.scheduler.set_begin_index(t_start * self.scheduler.order)
-
-        return timesteps, num_inference_steps - t_start
-
-    # Copied from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl_img2img.StableDiffusionXLImg2ImgPipeline.prepare_latents
-    def prepare_latents(
-        self, image, timestep, batch_size, num_images_per_prompt, dtype, device, generator=None, add_noise=True
-    ):
-        if not isinstance(image, (torch.Tensor, PIL.Image.Image, list)):
-            raise ValueError(
-                f"`image` has to be of type `torch.Tensor`, `PIL.Image.Image` or list but is {type(image)}"
-            )
-
-        # Offload text encoder if `enable_model_cpu_offload` was enabled
-        if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None:
-            torch.cuda.empty_cache()
-
-        image = image.to(device=device, dtype=dtype)
-
-        batch_size = batch_size * num_images_per_prompt
-
-        if image.shape[1] == 4:
-            init_latents = image
-
-        else:
-            # make sure the VAE is in float32 mode, as it overflows in float16
-            if self.vae.config.force_upcast:
-                image = image.float()
-                self.vae.to(dtype=torch.float32)
-
-            if isinstance(generator, list) and len(generator) != batch_size:
-                raise ValueError(
-                    f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
-                    f" size of {batch_size}. Make sure the batch size matches the length of the generators."
-                )
-
-            elif isinstance(generator, list):
-                init_latents = [
-                    retrieve_latents(self.vae.encode(image[i : i + 1]), generator=generator[i])
-                    for i in range(batch_size)
-                ]
-                init_latents = torch.cat(init_latents, dim=0)
-            else:
-                init_latents = retrieve_latents(self.vae.encode(image), generator=generator)
-
-            if self.vae.config.force_upcast:
-                self.vae.to(dtype)
-
-            init_latents = init_latents.to(dtype)
-            
-            init_latents = self.vae.config.scaling_factor * init_latents
-
-        if batch_size > init_latents.shape[0] and batch_size % init_latents.shape[0] == 0:
-            # expand init_latents for batch_size
-            additional_image_per_prompt = batch_size // init_latents.shape[0]
-            init_latents = torch.cat([init_latents] * additional_image_per_prompt, dim=0)
-        elif batch_size > init_latents.shape[0] and batch_size % init_latents.shape[0] != 0:
-            raise ValueError(
-                f"Cannot duplicate `image` of batch size {init_latents.shape[0]} to {batch_size} text prompts."
-            )
-        else:
-            init_latents = torch.cat([init_latents], dim=0)
-
-        if add_noise:
-            shape = init_latents.shape
-            noise = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-            # get latents
-            init_latents = self.scheduler.add_noise(init_latents, noise, timestep)
-
-        latents = init_latents
-
-        return latents
-
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
-    def prepare_latents_t2i(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
-        if isinstance(generator, list) and len(generator) != batch_size:
-            raise ValueError(
-                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
-                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
-            )
-
-        if latents is None:
-            latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-        else:
-            latents = latents.to(device)
-
-        # scale the initial noise by the standard deviation required by the scheduler
-        latents = latents * self.scheduler.init_noise_sigma
-        return latents
-
-
-
-    def _get_add_time_ids(self, original_size, crops_coords_top_left, target_size, dtype):
-        add_time_ids = list(original_size + crops_coords_top_left + target_size)
-
-        passed_add_embed_dim = (
-            self.unet.config.addition_time_embed_dim * len(add_time_ids) + 4096
-        )
-        expected_add_embed_dim = self.unet.add_embedding.linear_1.in_features
-
-        if expected_add_embed_dim != passed_add_embed_dim:
-            raise ValueError(
-                f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. The model has an incorrect config. Please check `unet.config.time_embedding_type` and `text_encoder_2.config.projection_dim`."
-            )
-
-        add_time_ids = torch.tensor([add_time_ids], dtype=dtype)
-        return add_time_ids
-
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
-    def upcast_vae(self):
-        dtype = self.vae.dtype
-        self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
-
-    @property
-    def guidance_scale(self):
-        return self._guidance_scale
-
-    @property
-    def clip_skip(self):
-        return self._clip_skip
-
-    # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
-    # corresponds to doing no classifier free guidance.
-    @property
-    def do_classifier_free_guidance(self):
-        return self._guidance_scale > 1
-
-    @property
-    def cross_attention_kwargs(self):
-        return self._cross_attention_kwargs
-
-    @property
-    def num_timesteps(self):
-        return self._num_timesteps
-
-    @torch.no_grad()
-    def __call__(
-        self,
-        prompt: Union[str, List[str]] = None,
-        image: PipelineImageInput = None,
-        control_image: PipelineImageInput = None,
-        height: Optional[int] = None,
-        width: Optional[int] = None,
-        strength: float = 0.8,
-        num_inference_steps: int = 50,
-        guidance_scale: float = 5.0,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        num_images_per_prompt: Optional[int] = 1,
-        eta: float = 0.0,
-        guess_mode: bool = False,
-        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.Tensor] = None,
-        prompt_embeds: Optional[torch.Tensor] = None,
-        negative_prompt_embeds: Optional[torch.Tensor] = None,
-        pooled_prompt_embeds: Optional[torch.Tensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
-        ip_adapter_image: Optional[PipelineImageInput] = None,
-        ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
-        output_type: Optional[str] = "pil",
-        return_dict: bool = True,
-        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-        controlnet_conditioning_scale: Union[float, List[float]] = 0.8,
-        control_guidance_start: Union[float, List[float]] = 0.0,
-        control_guidance_end: Union[float, List[float]] = 1.0,
-        original_size: Tuple[int, int] = None,
-        crops_coords_top_left: Tuple[int, int] = (0, 0),
-        target_size: Tuple[int, int] = None,
-        clip_skip: Optional[int] = None,
-        callback_on_step_end: Optional[
-            Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
-        ] = None,
-        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
-        **kwargs,
-    ):
-        r"""
-        Function invoked when calling the pipeline for generation.
-
-        Args:
-            prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
-                instead.
-            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
-                    `List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
-                The initial image will be used as the starting point for the image generation process. Can also accept
-                image latents as `image`, if passing latents directly, it will not be encoded again.
-            control_image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
-                    `List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
-                The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
-                the type is specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also
-                be accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If height
-                and/or width are passed, `image` is resized according to them. If multiple ControlNets are specified in
-                init, images must be passed as a list such that each element of the list can be correctly batched for
-                input to a single controlnet.
-            height (`int`, *optional*, defaults to the size of control_image):
-                The height in pixels of the generated image. Anything below 512 pixels won't work well for
-                [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
-                and checkpoints that are not specifically fine-tuned on low resolutions.
-            width (`int`, *optional*, defaults to the size of control_image):
-                The width in pixels of the generated image. Anything below 512 pixels won't work well for
-                [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
-                and checkpoints that are not specifically fine-tuned on low resolutions.
-            strength (`float`, *optional*, defaults to 0.8):
-                Indicates extent to transform the reference `image`. Must be between 0 and 1. `image` is used as a
-                starting point and more noise is added the higher the `strength`. The number of denoising steps depends
-                on the amount of noise initially added. When `strength` is 1, added noise is maximum and the denoising
-                process runs for the full number of iterations specified in `num_inference_steps`. A value of 1
-                essentially ignores `image`.
-            num_inference_steps (`int`, *optional*, defaults to 50):
-                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
-                expense of slower inference.
-            guidance_scale (`float`, *optional*, defaults to 7.5):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            num_images_per_prompt (`int`, *optional*, defaults to 1):
-                The number of images to generate per prompt.
-            eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
-                [`schedulers.DDIMScheduler`], will be ignored for others.
-            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
-                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
-                to make generation deterministic.
-            latents (`torch.Tensor`, *optional*):
-                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
-                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
-                tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            pooled_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
-                If not provided, pooled text embeddings will be generated from `prompt` input argument.
-            negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
-                input argument.
-            ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
-            ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
-                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
-                contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
-            output_type (`str`, *optional*, defaults to `"pil"`):
-                The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
-                plain tuple.
-            cross_attention_kwargs (`dict`, *optional*):
-                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
-                `self.processor` in
-                [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
-            controlnet_conditioning_scale (`float` or `List[float]`, *optional*, defaults to 1.0):
-                The outputs of the controlnet are multiplied by `controlnet_conditioning_scale` before they are added
-                to the residual in the original unet. If multiple ControlNets are specified in init, you can set the
-                corresponding scale as a list.
-            control_guidance_start (`float` or `List[float]`, *optional*, defaults to 0.0):
-                The percentage of total steps at which the controlnet starts applying.
-            control_guidance_end (`float` or `List[float]`, *optional*, defaults to 1.0):
-                The percentage of total steps at which the controlnet stops applying.
-            original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
-                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
-                explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
-            crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
-                `crops_coords_top_left` can be used to generate an image that appears to be "cropped" from the position
-                `crops_coords_top_left` downwards. Favorable, well-centered images are usually achieved by setting
-                `crops_coords_top_left` to (0, 0). Part of SDXL's micro-conditioning as explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
-            target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                For most cases, `target_size` should be set to the desired height and width of the generated image. If
-                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
-                section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
-            clip_skip (`int`, *optional*):
-                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
-                the output of the pre-final layer will be used for computing the prompt embeddings.
-            callback_on_step_end (`Callable`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
-                A function or a subclass of `PipelineCallback` or `MultiPipelineCallbacks` that is called at the end of
-                each denoising step during the inference. with the following arguments: `callback_on_step_end(self:
-                DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)`. `callback_kwargs` will include a
-                list of all tensors as specified by `callback_on_step_end_tensor_inputs`.
-            callback_on_step_end_tensor_inputs (`List`, *optional*):
-                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
-                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeline class.
-
-        Examples:
-
-        Returns:
-            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
-            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] if `return_dict` is True, otherwise a `tuple`
-            containing the output images.
-        """
-
-        callback = kwargs.pop("callback", None)
-        callback_steps = kwargs.pop("callback_steps", None)
-
-        if callback is not None:
-            deprecate(
-                "callback",
-                "1.0.0",
-                "Passing `callback` as an input argument to `__call__` is deprecated, consider using `callback_on_step_end`",
-            )
-        if callback_steps is not None:
-            deprecate(
-                "callback_steps",
-                "1.0.0",
-                "Passing `callback_steps` as an input argument to `__call__` is deprecated, consider using `callback_on_step_end`",
-            )
-
-        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
-            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs
-
-        controlnet = self.controlnet._orig_mod if is_compiled_module(self.controlnet) else self.controlnet
-
-        # align format for control guidance
-        if not isinstance(control_guidance_start, list) and isinstance(control_guidance_end, list):
-            control_guidance_start = len(control_guidance_end) * [control_guidance_start]
-        elif not isinstance(control_guidance_end, list) and isinstance(control_guidance_start, list):
-            control_guidance_end = len(control_guidance_start) * [control_guidance_end]
-        elif not isinstance(control_guidance_start, list) and not isinstance(control_guidance_end, list):
-            mult = len(controlnet.nets) if isinstance(controlnet, MultiControlNetModel) else 1
-            control_guidance_start, control_guidance_end = (
-                mult * [control_guidance_start],
-                mult * [control_guidance_end],
-            )
-
-        # from IPython import embed; embed()
-        # 1. Check inputs. Raise error if not correct
-        self.check_inputs(
-            prompt,
-            control_image,
-            strength,
-            num_inference_steps,
-            callback_steps,
-            negative_prompt,
-            prompt_embeds,
-            negative_prompt_embeds,
-            pooled_prompt_embeds,
-            negative_pooled_prompt_embeds,
-            ip_adapter_image,
-            ip_adapter_image_embeds,
-            controlnet_conditioning_scale,
-            control_guidance_start,
-            control_guidance_end,
-            callback_on_step_end_tensor_inputs,
-        )
-
-        self._guidance_scale = guidance_scale
-        self._clip_skip = clip_skip
-        self._cross_attention_kwargs = cross_attention_kwargs
-
-        # 2. Define call parameters
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        device = self._execution_device
-
-        if isinstance(controlnet, MultiControlNetModel) and isinstance(controlnet_conditioning_scale, float):
-            controlnet_conditioning_scale = [controlnet_conditioning_scale] * len(controlnet.nets)
-
-        # 3.1. Encode input prompt
-        text_encoder_lora_scale = (
-            self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
-        )
-        (
-            prompt_embeds,
-            negative_prompt_embeds,
-            pooled_prompt_embeds,
-            negative_pooled_prompt_embeds,
-        ) = self.encode_prompt(
-            prompt,
-            device,
-            num_images_per_prompt,
-            self.do_classifier_free_guidance,
-            negative_prompt,
-            prompt_embeds=prompt_embeds,
-            negative_prompt_embeds=negative_prompt_embeds,
-            pooled_prompt_embeds=pooled_prompt_embeds,
-            negative_pooled_prompt_embeds=negative_pooled_prompt_embeds,
-            lora_scale=text_encoder_lora_scale,
-        )
-
-        # 3.2 Encode ip_adapter_image
-        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
-            image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image,
-                ip_adapter_image_embeds,
-                device,
-                batch_size * num_images_per_prompt,
-                self.do_classifier_free_guidance,
-            )
-
-        # 4. Prepare image and controlnet_conditioning_image
-        image = self.image_processor.preprocess(image, height=height, width=width).to(dtype=torch.float32)
-
-        if isinstance(controlnet, ControlNetModel):
-            control_image = self.prepare_control_image(
-                image=control_image,
-                width=width,
-                height=height,
-                batch_size=batch_size * num_images_per_prompt,
-                num_images_per_prompt=num_images_per_prompt,
-                device=device,
-                dtype=controlnet.dtype,
-                do_classifier_free_guidance=self.do_classifier_free_guidance,
-                guess_mode=guess_mode,
-            )
-            height, width = control_image.shape[-2:]
-        elif isinstance(controlnet, MultiControlNetModel):
-            control_images = []
-
-            for control_image_ in control_image:
-                control_image_ = self.prepare_control_image(
-                    image=control_image_,
-                    width=width,
-                    height=height,
-                    batch_size=batch_size * num_images_per_prompt,
-                    num_images_per_prompt=num_images_per_prompt,
-                    device=device,
-                    dtype=controlnet.dtype,
-                    do_classifier_free_guidance=self.do_classifier_free_guidance,
-                    guess_mode=guess_mode,
-                )
-
-                control_images.append(control_image_)
-
-            control_image = control_images
-            height, width = control_image[0].shape[-2:]
-        else:
-            assert False
-
-        # 5. Prepare timesteps
-        self.scheduler.set_timesteps(num_inference_steps, device=device)
-        timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, strength, device)
-        latent_timestep = timesteps[:1].repeat(batch_size * num_images_per_prompt)
-        self._num_timesteps = len(timesteps)
-
-        # 6. Prepare latent variables
-
-        num_channels_latents = self.unet.config.in_channels
-        if latents is None:
-            if strength >= 1.0:
-                latents = self.prepare_latents_t2i(
-                    batch_size * num_images_per_prompt,
-                    num_channels_latents,
-                    height,
-                    width,
-                    prompt_embeds.dtype,
-                    device,
-                    generator,
-                    latents,
-                )
-            else:
-                latents = self.prepare_latents(
-                    image,
-                    latent_timestep,
-                    batch_size,
-                    num_images_per_prompt,
-                    prompt_embeds.dtype,
-                    device,
-                    generator,
-                    True,
-                )
-                
-        
-        # 7. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
-        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
-
-        # 7.1 Create tensor stating which controlnets to keep
-        controlnet_keep = []
-        for i in range(len(timesteps)):
-            keeps = [
-                1.0 - float(i / len(timesteps) < s or (i + 1) / len(timesteps) > e)
-                for s, e in zip(control_guidance_start, control_guidance_end)
-            ]
-            controlnet_keep.append(keeps[0] if isinstance(controlnet, ControlNetModel) else keeps)
-
-        # 7.2 Prepare added time ids & embeddings
-        if isinstance(control_image, list):
-            original_size = original_size or control_image[0].shape[-2:]
-        else:
-            original_size = original_size or control_image.shape[-2:]
-        target_size = target_size or (height, width)
-
-        # 7. Prepare added time ids & embeddings
-        add_text_embeds = pooled_prompt_embeds
-        add_time_ids = self._get_add_time_ids(
-            original_size, crops_coords_top_left, target_size, dtype=prompt_embeds.dtype
-        )
-
-        if self.do_classifier_free_guidance:
-            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
-            add_text_embeds = torch.cat([negative_pooled_prompt_embeds, add_text_embeds], dim=0)
-            add_time_ids = torch.cat([add_time_ids, add_time_ids], dim=0)
-
-        prompt_embeds = prompt_embeds.to(device)
-        add_text_embeds = add_text_embeds.to(device)
-        add_time_ids = add_time_ids.to(device).repeat(batch_size * num_images_per_prompt, 1)
-
-        # 8. Denoising loop
-        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            for i, t in enumerate(timesteps):
-                # expand the latents if we are doing classifier free guidance
-                latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
-                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
-
-                added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
-
-                # controlnet(s) inference
-                if guess_mode and self.do_classifier_free_guidance:
-                    # Infer ControlNet only for the conditional batch.
-                    control_model_input = latents
-                    control_model_input = self.scheduler.scale_model_input(control_model_input, t)
-                    controlnet_prompt_embeds = prompt_embeds.chunk(2)[1]
-                    controlnet_added_cond_kwargs = {
-                        "text_embeds": add_text_embeds.chunk(2)[1],
-                        "time_ids": add_time_ids.chunk(2)[1],
-                    }
-                else:
-                    control_model_input = latent_model_input
-                    controlnet_prompt_embeds = prompt_embeds
-                    controlnet_added_cond_kwargs = added_cond_kwargs
-
-                if isinstance(controlnet_keep[i], list):
-                    cond_scale = [c * s for c, s in zip(controlnet_conditioning_scale, controlnet_keep[i])]
-                else:
-                    controlnet_cond_scale = controlnet_conditioning_scale
-                    if isinstance(controlnet_cond_scale, list):
-                        controlnet_cond_scale = controlnet_cond_scale[0]
-                    cond_scale = controlnet_cond_scale * controlnet_keep[i]
-
-                down_block_res_samples, mid_block_res_sample = self.controlnet(
-                    control_model_input,
-                    t,
-                    encoder_hidden_states=controlnet_prompt_embeds,
-                    controlnet_cond=control_image,
-                    conditioning_scale=cond_scale,
-                    guess_mode=guess_mode,
-                    added_cond_kwargs=controlnet_added_cond_kwargs,
-                    return_dict=False,
-                )
-
-                if guess_mode and self.do_classifier_free_guidance:
-                    # Infered ControlNet only for the conditional batch.
-                    # To apply the output of ControlNet to both the unconditional and conditional batches,
-                    # add 0 to the unconditional batch to keep it unchanged.
-                    down_block_res_samples = [torch.cat([torch.zeros_like(d), d]) for d in down_block_res_samples]
-                    mid_block_res_sample = torch.cat([torch.zeros_like(mid_block_res_sample), mid_block_res_sample])
-
-                if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
-                    added_cond_kwargs["image_embeds"] = image_embeds
-
-                # predict the noise residual
-                noise_pred = self.unet(
-                    latent_model_input,
-                    t,
-                    encoder_hidden_states=prompt_embeds,
-                    cross_attention_kwargs=self.cross_attention_kwargs,
-                    down_block_additional_residuals=down_block_res_samples,
-                    mid_block_additional_residual=mid_block_res_sample,
-                    added_cond_kwargs=added_cond_kwargs,
-                    return_dict=False,
-                )[0]
-
-                # perform guidance
-                if self.do_classifier_free_guidance:
-                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
-
-                # compute the previous noisy sample x_t -> x_t-1
-                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
-
-                # call the callback, if provided
-                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
-                    progress_bar.update()
-                    if callback is not None and i % callback_steps == 0:
-                        step_idx = i // getattr(self.scheduler, "order", 1)
-                        callback(step_idx, t, latents)
-
-        # If we do sequential model offloading, let's offload unet and controlnet
-        # manually for max memory savings
-        if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None:
-            self.unet.to("cpu")
-            self.controlnet.to("cpu")
-            torch.cuda.empty_cache()
-
-        if not output_type == "latent":
-            # make sure the VAE is in float32 mode, as it overflows in float16
-            needs_upcasting = self.vae.dtype == torch.float16 and self.vae.config.force_upcast
-
-            if needs_upcasting:
-                self.upcast_vae()
-                latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)
-
-            latents = latents / self.vae.config.scaling_factor
-            image = self.vae.decode(latents, return_dict=False)[0]
-
-            # cast back to fp16 if needed
-            if needs_upcasting:
-                self.vae.to(dtype=torch.float16)
-        else:
-            image = latents
-            return StableDiffusionXLPipelineOutput(images=image)
-
-        image = self.image_processor.postprocess(image, output_type=output_type)
-
-        # Offload all models
-        self.maybe_free_model_hooks()
-
-        if not return_dict:
-            return (image,)
-
-        return StableDiffusionXLPipelineOutput(images=image)

kolors/pipelines/pipeline_stable_diffusion_xl_chatglm_256.py

@@ -1,841 +0,0 @@
-# Copyright 2023 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-import sys
-import os
-sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
-from kolors.models.modeling_chatglm import ChatGLMModel
-from kolors.models.tokenization_chatglm import ChatGLMTokenizer
-import inspect
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
-import torch
-from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer
-from transformers import XLMRobertaModel, ChineseCLIPTextModel
-
-from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInversionLoaderMixin
-from diffusers.models import AutoencoderKL, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
-    XFormersAttnProcessor,
-)
-from diffusers.schedulers import KarrasDiffusionSchedulers
-from diffusers.utils import (
-    is_accelerate_available,
-    is_accelerate_version,
-    logging,
-    replace_example_docstring,
-)
-try:
-    from diffusers.utils import randn_tensor
-except:
-    from diffusers.utils.torch_utils import randn_tensor
-from diffusers.pipelines.pipeline_utils import DiffusionPipeline
-from diffusers.pipelines.stable_diffusion_xl import StableDiffusionXLPipelineOutput
-
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-EXAMPLE_DOC_STRING = """
-    Examples:
-        ```py
-        >>> import torch
-        >>> from diffusers import StableDiffusionXLPipeline
-
-        >>> pipe = StableDiffusionXLPipeline.from_pretrained(
-        ...     "stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16
-        ... )
-        >>> pipe = pipe.to("cuda")
-
-        >>> prompt = "a photo of an astronaut riding a horse on mars"
-        >>> image = pipe(prompt).images[0]
-        ```
-"""
-
-
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.rescale_noise_cfg
-def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
-    """
-    Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and
-    Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf). See Section 3.4
-    """
-    std_text = noise_pred_text.std(dim=list(range(1, noise_pred_text.ndim)), keepdim=True)
-    std_cfg = noise_cfg.std(dim=list(range(1, noise_cfg.ndim)), keepdim=True)
-    # rescale the results from guidance (fixes overexposure)
-    noise_pred_rescaled = noise_cfg * (std_text / std_cfg)
-    # mix with the original results from guidance by factor guidance_rescale to avoid "plain looking" images
-    noise_cfg = guidance_rescale * noise_pred_rescaled + (1 - guidance_rescale) * noise_cfg
-    return noise_cfg
-
-
-class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoaderMixin):
-    r"""
-    Pipeline for text-to-image generation using Stable Diffusion XL.
-
-    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
-    library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
-
-    In addition the pipeline inherits the following loading methods:
-        - *Textual-Inversion*: [`loaders.TextualInversionLoaderMixin.load_textual_inversion`]
-        - *LoRA*: [`loaders.LoraLoaderMixin.load_lora_weights`]
-        - *Ckpt*: [`loaders.FromSingleFileMixin.from_single_file`]
-
-    as well as the following saving methods:
-        - *LoRA*: [`loaders.LoraLoaderMixin.save_lora_weights`]
-
-    Args:
-        vae ([`AutoencoderKL`]):
-            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
-        text_encoder ([`CLIPTextModel`]):
-            Frozen text-encoder. Stable Diffusion XL uses the text portion of
-            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel), specifically
-            the [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) variant.
-
-        tokenizer (`CLIPTokenizer`):
-            Tokenizer of class
-            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
-
-        unet ([`UNet2DConditionModel`]): Conditional U-Net architecture to denoise the encoded image latents.
-        scheduler ([`SchedulerMixin`]):
-            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
-            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
-    """
-
-    def __init__(
-        self,
-        vae: AutoencoderKL,
-        text_encoder: ChatGLMModel,
-        tokenizer: ChatGLMTokenizer,
-        unet: UNet2DConditionModel,
-        scheduler: KarrasDiffusionSchedulers,
-        force_zeros_for_empty_prompt: bool = True,
-    ):
-        super().__init__()
-
-        self.register_modules(
-            vae=vae,
-            text_encoder=text_encoder,
-            tokenizer=tokenizer,
-            unet=unet,
-            scheduler=scheduler,
-        )
-        self.register_to_config(force_zeros_for_empty_prompt=force_zeros_for_empty_prompt)
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
-        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
-        self.default_sample_size = self.unet.config.sample_size
-
-        # self.watermark = StableDiffusionXLWatermarker()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_vae_slicing
-    def enable_vae_slicing(self):
-        r"""
-        Enable sliced VAE decoding.
-
-        When this option is enabled, the VAE will split the input tensor in slices to compute decoding in several
-        steps. This is useful to save some memory and allow larger batch sizes.
-        """
-        self.vae.enable_slicing()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_vae_slicing
-    def disable_vae_slicing(self):
-        r"""
-        Disable sliced VAE decoding. If `enable_vae_slicing` was previously invoked, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_slicing()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_vae_tiling
-    def enable_vae_tiling(self):
-        r"""
-        Enable tiled VAE decoding.
-
-        When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and encoding in
-        several steps. This is useful to save a large amount of memory and to allow the processing of larger images.
-        """
-        self.vae.enable_tiling()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_vae_tiling
-    def disable_vae_tiling(self):
-        r"""
-        Disable tiled VAE decoding. If `enable_vae_tiling` was previously invoked, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_tiling()
-
-    def enable_sequential_cpu_offload(self, gpu_id=0):
-        r"""
-        Offloads all models to CPU using accelerate, significantly reducing memory usage. When called, unet,
-        text_encoder, vae and safety checker have their state dicts saved to CPU and then are moved to a
-        `torch.device('meta') and loaded to GPU only when their specific submodule has its `forward` method called.
-        Note that offloading happens on a submodule basis. Memory savings are higher than with
-        `enable_model_cpu_offload`, but performance is lower.
-        """
-        if is_accelerate_available() and is_accelerate_version(">=", "0.14.0"):
-            from accelerate import cpu_offload
-        else:
-            raise ImportError("`enable_sequential_cpu_offload` requires `accelerate v0.14.0` or higher")
-
-        device = torch.device(f"cuda:{gpu_id}")
-
-        if self.device.type != "cpu":
-            self.to("cpu", silence_dtype_warnings=True)
-            torch.cuda.empty_cache()  # otherwise we don't see the memory savings (but they probably exist)
-
-        for cpu_offloaded_model in [self.unet, self.text_encoder, self.vae]:
-            cpu_offload(cpu_offloaded_model, device)
-
-    def enable_model_cpu_offload(self, gpu_id=0):
-        r"""
-        Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared
-        to `enable_sequential_cpu_offload`, this method moves one whole model at a time to the GPU when its `forward`
-        method is called, and the model remains in GPU until the next model runs. Memory savings are lower than with
-        `enable_sequential_cpu_offload`, but performance is much better due to the iterative execution of the `unet`.
-        """
-        if is_accelerate_available() and is_accelerate_version(">=", "0.17.0.dev0"):
-            from accelerate import cpu_offload_with_hook
-        else:
-            raise ImportError("`enable_model_cpu_offload` requires `accelerate v0.17.0` or higher.")
-
-        device = torch.device(f"cuda:{gpu_id}")
-
-        if self.device.type != "cpu":
-            self.to("cpu", silence_dtype_warnings=True)
-            torch.cuda.empty_cache()  # otherwise we don't see the memory savings (but they probably exist)
-
-        model_sequence = (
-            [self.text_encoder]
-        )
-        model_sequence.extend([self.unet, self.vae])
-
-        hook = None
-        for cpu_offloaded_model in model_sequence:
-            _, hook = cpu_offload_with_hook(cpu_offloaded_model, device, prev_module_hook=hook)
-
-        # We'll offload the last model manually.
-        self.final_offload_hook = hook
-
-    @property
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline._execution_device
-    def _execution_device(self):
-        r"""
-        Returns the device on which the pipeline's models will be executed. After calling
-        `pipeline.enable_sequential_cpu_offload()` the execution device can only be inferred from Accelerate's module
-        hooks.
-        """
-        if not hasattr(self.unet, "_hf_hook"):
-            return self.device
-        for module in self.unet.modules():
-            if (
-                hasattr(module, "_hf_hook")
-                and hasattr(module._hf_hook, "execution_device")
-                and module._hf_hook.execution_device is not None
-            ):
-                return torch.device(module._hf_hook.execution_device)
-        return self.device
-
-    def encode_prompt(
-        self,
-        prompt,
-        device: Optional[torch.device] = None,
-        num_images_per_prompt: int = 1,
-        do_classifier_free_guidance: bool = True,
-        negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        lora_scale: Optional[float] = None,
-    ):
-        r"""
-        Encodes the prompt into text encoder hidden states.
-
-        Args:
-             prompt (`str` or `List[str]`, *optional*):
-                prompt to be encoded
-            device: (`torch.device`):
-                torch device
-            num_images_per_prompt (`int`):
-                number of images that should be generated per prompt
-            do_classifier_free_guidance (`bool`):
-                whether to use classifier free guidance or not
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
-                If not provided, pooled text embeddings will be generated from `prompt` input argument.
-            negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
-                input argument.
-            lora_scale (`float`, *optional*):
-                A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
-        """
-        # from IPython import embed; embed(); exit()
-        device = device or self._execution_device
-
-        # set lora scale so that monkey patched LoRA
-        # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
-            self._lora_scale = lora_scale
-
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        # Define tokenizers and text encoders
-        tokenizers = [self.tokenizer]
-        text_encoders = [self.text_encoder]
-
-        if prompt_embeds is None:
-            # textual inversion: procecss multi-vector tokens if necessary
-            prompt_embeds_list = []
-            for tokenizer, text_encoder in zip(tokenizers, text_encoders):
-                if isinstance(self, TextualInversionLoaderMixin):
-                    prompt = self.maybe_convert_prompt(prompt, tokenizer)
-
-                text_inputs = tokenizer(
-                    prompt,
-                    padding="max_length",
-                    max_length=256,
-                    truncation=True,
-                    return_tensors="pt",
-                ).to('cuda')
-                output = text_encoder(
-                        input_ids=text_inputs['input_ids'] ,
-                        attention_mask=text_inputs['attention_mask'],
-                        position_ids=text_inputs['position_ids'],
-                        output_hidden_states=True)
-                prompt_embeds = output.hidden_states[-2].permute(1, 0, 2).clone()
-                pooled_prompt_embeds = output.hidden_states[-1][-1, :, :].clone() # [batch_size, 4096]
-                bs_embed, seq_len, _ = prompt_embeds.shape
-                prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
-                prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)
-
-                prompt_embeds_list.append(prompt_embeds)
-
-            # prompt_embeds = torch.concat(prompt_embeds_list, dim=-1)
-            prompt_embeds = prompt_embeds_list[0]
-
-        # get unconditional embeddings for classifier free guidance
-        zero_out_negative_prompt = negative_prompt is None and self.config.force_zeros_for_empty_prompt
-        if do_classifier_free_guidance and negative_prompt_embeds is None and zero_out_negative_prompt:
-            negative_prompt_embeds = torch.zeros_like(prompt_embeds)
-            negative_pooled_prompt_embeds = torch.zeros_like(pooled_prompt_embeds)
-        elif do_classifier_free_guidance and negative_prompt_embeds is None:
-            # negative_prompt = negative_prompt or ""
-            uncond_tokens: List[str]
-            if negative_prompt is None:
-                uncond_tokens = [""] * batch_size
-            elif prompt is not None and type(prompt) is not type(negative_prompt):
-                raise TypeError(
-                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
-                    f" {type(prompt)}."
-                )
-            elif isinstance(negative_prompt, str):
-                uncond_tokens = [negative_prompt]
-            elif batch_size != len(negative_prompt):
-                raise ValueError(
-                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
-                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
-                    " the batch size of `prompt`."
-                )
-            else:
-                uncond_tokens = negative_prompt
-
-            negative_prompt_embeds_list = []
-            for tokenizer, text_encoder in zip(tokenizers, text_encoders):
-                # textual inversion: procecss multi-vector tokens if necessary
-                if isinstance(self, TextualInversionLoaderMixin):
-                    uncond_tokens = self.maybe_convert_prompt(uncond_tokens, tokenizer)
-
-                max_length = prompt_embeds.shape[1]
-                uncond_input = tokenizer(
-                    uncond_tokens,
-                    padding="max_length",
-                    max_length=max_length,
-                    truncation=True,
-                    return_tensors="pt",
-                ).to('cuda')
-                output = text_encoder(
-                        input_ids=uncond_input['input_ids'] ,
-                        attention_mask=uncond_input['attention_mask'],
-                        position_ids=uncond_input['position_ids'],
-                        output_hidden_states=True)
-                negative_prompt_embeds = output.hidden_states[-2].permute(1, 0, 2).clone()
-                negative_pooled_prompt_embeds = output.hidden_states[-1][-1, :, :].clone() # [batch_size, 4096]
-
-                if do_classifier_free_guidance:
-                    # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
-                    seq_len = negative_prompt_embeds.shape[1]
-
-                    negative_prompt_embeds = negative_prompt_embeds.to(dtype=text_encoder.dtype, device=device)
-
-                    negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
-                    negative_prompt_embeds = negative_prompt_embeds.view(
-                        batch_size * num_images_per_prompt, seq_len, -1
-                    )
-
-                    # For classifier free guidance, we need to do two forward passes.
-                    # Here we concatenate the unconditional and text embeddings into a single batch
-                    # to avoid doing two forward passes
-
-                negative_prompt_embeds_list.append(negative_prompt_embeds)
-
-            # negative_prompt_embeds = torch.concat(negative_prompt_embeds_list, dim=-1)
-            negative_prompt_embeds = negative_prompt_embeds_list[0]
-
-        bs_embed = pooled_prompt_embeds.shape[0]
-        pooled_prompt_embeds = pooled_prompt_embeds.repeat(1, num_images_per_prompt).view(
-            bs_embed * num_images_per_prompt, -1
-        )
-        if do_classifier_free_guidance:
-            negative_pooled_prompt_embeds = negative_pooled_prompt_embeds.repeat(1, num_images_per_prompt).view(
-                bs_embed * num_images_per_prompt, -1
-            )
-
-        return prompt_embeds, negative_prompt_embeds, pooled_prompt_embeds, negative_pooled_prompt_embeds
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
-    def prepare_extra_step_kwargs(self, generator, eta):
-        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
-        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
-        # and should be between [0, 1]
-
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        # check if the scheduler accepts generator
-        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        if accepts_generator:
-            extra_step_kwargs["generator"] = generator
-        return extra_step_kwargs
-
-    def check_inputs(
-        self,
-        prompt,
-        height,
-        width,
-        callback_steps,
-        negative_prompt=None,
-        prompt_embeds=None,
-        negative_prompt_embeds=None,
-        pooled_prompt_embeds=None,
-        negative_pooled_prompt_embeds=None,
-    ):
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
-
-        if (callback_steps is None) or (
-            callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0)
-        ):
-            raise ValueError(
-                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
-                f" {type(callback_steps)}."
-            )
-
-        if prompt is not None and prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
-                " only forward one of the two."
-            )
-        elif prompt is None and prompt_embeds is None:
-            raise ValueError(
-                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
-            )
-        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
-            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
-
-        if negative_prompt is not None and negative_prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
-                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
-            )
-
-        if prompt_embeds is not None and negative_prompt_embeds is not None:
-            if prompt_embeds.shape != negative_prompt_embeds.shape:
-                raise ValueError(
-                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
-                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
-                    f" {negative_prompt_embeds.shape}."
-                )
-
-        if prompt_embeds is not None and pooled_prompt_embeds is None:
-            raise ValueError(
-                "If `prompt_embeds` are provided, `pooled_prompt_embeds` also have to be passed. Make sure to generate `pooled_prompt_embeds` from the same text encoder that was used to generate `prompt_embeds`."
-            )
-
-        if negative_prompt_embeds is not None and negative_pooled_prompt_embeds is None:
-            raise ValueError(
-                "If `negative_prompt_embeds` are provided, `negative_pooled_prompt_embeds` also have to be passed. Make sure to generate `negative_pooled_prompt_embeds` from the same text encoder that was used to generate `negative_prompt_embeds`."
-            )
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
-    def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
-        if isinstance(generator, list) and len(generator) != batch_size:
-            raise ValueError(
-                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
-                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
-            )
-
-        if latents is None:
-            latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-        else:
-            latents = latents.to(device)
-
-        # scale the initial noise by the standard deviation required by the scheduler
-        latents = latents * self.scheduler.init_noise_sigma
-        return latents
-
-    def _get_add_time_ids(self, original_size, crops_coords_top_left, target_size, dtype):
-        add_time_ids = list(original_size + crops_coords_top_left + target_size)
-
-        passed_add_embed_dim = (
-            self.unet.config.addition_time_embed_dim * len(add_time_ids) + 4096
-        )
-        expected_add_embed_dim = self.unet.add_embedding.linear_1.in_features
-
-        if expected_add_embed_dim != passed_add_embed_dim:
-            raise ValueError(
-                f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. The model has an incorrect config. Please check `unet.config.time_embedding_type` and `text_encoder_2.config.projection_dim`."
-            )
-
-        add_time_ids = torch.tensor([add_time_ids], dtype=dtype)
-        return add_time_ids
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
-    def upcast_vae(self):
-        dtype = self.vae.dtype
-        self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
-
-    @torch.no_grad()
-    @replace_example_docstring(EXAMPLE_DOC_STRING)
-    def __call__(
-        self,
-        prompt: Union[str, List[str]] = None,
-        height: Optional[int] = None,
-        width: Optional[int] = None,
-        num_inference_steps: int = 50,
-        denoising_end: Optional[float] = None,
-        guidance_scale: float = 5.0,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        num_images_per_prompt: Optional[int] = 1,
-        eta: float = 0.0,
-        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        output_type: Optional[str] = "pil",
-        return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
-        callback_steps: int = 1,
-        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-        guidance_rescale: float = 0.0,
-        original_size: Optional[Tuple[int, int]] = None,
-        crops_coords_top_left: Tuple[int, int] = (0, 0),
-        target_size: Optional[Tuple[int, int]] = None,
-        use_dynamic_threshold: Optional[bool] = False,
-    ):
-        r"""
-        Function invoked when calling the pipeline for generation.
-
-        Args:
-            prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
-                instead.
-            height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The height in pixels of the generated image.
-            width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The width in pixels of the generated image.
-            num_inference_steps (`int`, *optional*, defaults to 50):
-                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
-                expense of slower inference.
-            denoising_end (`float`, *optional*):
-                When specified, determines the fraction (between 0.0 and 1.0) of the total denoising process to be
-                completed before it is intentionally prematurely terminated. For instance, if denoising_end is set to
-                0.7 and `num_inference_steps` is fixed at 50, the process will execute only 35 (i.e., 0.7 * 50)
-                Denoisers" multi-pipeline setup, as elaborated in [**Refining the Image
-                Output**](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl#refining-the-image-output)
-            guidance_scale (`float`, *optional*, defaults to 7.5):
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            num_images_per_prompt (`int`, *optional*, defaults to 1):
-                The number of images to generate per prompt.
-            eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
-                [`schedulers.DDIMScheduler`], will be ignored for others.
-            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
-                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
-                to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
-                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
-                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
-                tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
-                If not provided, pooled text embeddings will be generated from `prompt` input argument.
-            negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-            output_type (`str`, *optional*, defaults to `"pil"`):
-                The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionXLPipelineOutput`] instead of a
-            callback (`Callable`, *optional*):
-                A function that will be called every `callback_steps` steps during inference. The function will be
-            callback_steps (`int`, *optional*, defaults to 1):
-                The frequency at which the `callback` function will be called. If not specified, the callback will be
-                called at every step.
-            cross_attention_kwargs (`dict`, *optional*):
-                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
-                `self.processor` in
-                [diffusers.cross_attention](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/cross_attention.py).
-            guidance_rescale (`float`, *optional*, defaults to 0.7):
-                Guidance rescale factor proposed by [Common Diffusion Noise Schedules and Sample Steps are
-                Flawed](https://arxiv.org/pdf/2305.08891.pdf) `guidance_scale` is defined as `φ` in equation 16. of
-                [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf).
-                Guidance rescale factor should fix overexposure when using zero terminal SNR.
-            original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                TODO
-            crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
-                TODO
-            target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                TODO
-
-        Examples:
-
-        Returns:
-            [`~pipelines.stable_diffusion.StableDiffusionXLPipelineOutput`] or `tuple`:
-            [`~pipelines.stable_diffusion.StableDiffusionXLPipelineOutput`] if `return_dict` is True, otherwise a
-            `tuple. When returning a tuple, the first element is a list with the generated images, and the second
-            element is a list of `bool`s denoting whether the corresponding generated image likely represents
-            "not-safe-for-work" (nsfw) content, according to the `safety_checker`.
-        """
-        # 0. Default height and width to unet
-        height = height or self.default_sample_size * self.vae_scale_factor
-        width = width or self.default_sample_size * self.vae_scale_factor
-
-        original_size = original_size or (height, width)
-        target_size = target_size or (height, width)
-
-        # 1. Check inputs. Raise error if not correct
-        self.check_inputs(
-            prompt,
-            height,
-            width,
-            callback_steps,
-            negative_prompt,
-            prompt_embeds,
-            negative_prompt_embeds,
-            pooled_prompt_embeds,
-            negative_pooled_prompt_embeds,
-        )
-
-        # 2. Define call parameters
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        device = self._execution_device
-
-        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
-        # corresponds to doing no classifier free guidance.
-        do_classifier_free_guidance = guidance_scale > 1.0
-
-        # 3. Encode input prompt
-        text_encoder_lora_scale = (
-            cross_attention_kwargs.get("scale", None) if cross_attention_kwargs is not None else None
-        )
-        (
-            prompt_embeds,
-            negative_prompt_embeds,
-            pooled_prompt_embeds,
-            negative_pooled_prompt_embeds,
-        ) = self.encode_prompt(
-            prompt,
-            device,
-            num_images_per_prompt,
-            do_classifier_free_guidance,
-            negative_prompt,
-            prompt_embeds=prompt_embeds,
-            negative_prompt_embeds=negative_prompt_embeds,
-            pooled_prompt_embeds=pooled_prompt_embeds,
-            negative_pooled_prompt_embeds=negative_pooled_prompt_embeds,
-            lora_scale=text_encoder_lora_scale,
-        )
-
-        # 4. Prepare timesteps
-        self.scheduler.set_timesteps(num_inference_steps, device=device)
-
-        timesteps = self.scheduler.timesteps
-
-        # 5. Prepare latent variables
-        num_channels_latents = self.unet.config.in_channels
-        latents = self.prepare_latents(
-            batch_size * num_images_per_prompt,
-            num_channels_latents,
-            height,
-            width,
-            prompt_embeds.dtype,
-            device,
-            generator,
-            latents,
-        )
-
-        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
-        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
-
-        # 7. Prepare added time ids & embeddings
-        add_text_embeds = pooled_prompt_embeds
-        add_time_ids = self._get_add_time_ids(
-            original_size, crops_coords_top_left, target_size, dtype=prompt_embeds.dtype
-        )
-
-        if do_classifier_free_guidance:
-            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
-            add_text_embeds = torch.cat([negative_pooled_prompt_embeds, add_text_embeds], dim=0)
-            add_time_ids = torch.cat([add_time_ids, add_time_ids], dim=0)
-
-        prompt_embeds = prompt_embeds.to(device)
-        add_text_embeds = add_text_embeds.to(device)
-        add_time_ids = add_time_ids.to(device).repeat(batch_size * num_images_per_prompt, 1)
-
-        # 8. Denoising loop
-        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
-
-        # 7.1 Apply denoising_end
-        if denoising_end is not None:
-            num_inference_steps = int(round(denoising_end * num_inference_steps))
-            timesteps = timesteps[: num_warmup_steps + self.scheduler.order * num_inference_steps]
-
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            for i, t in enumerate(timesteps):
-                # expand the latents if we are doing classifier free guidance
-                latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
-
-                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
-
-                # predict the noise residual
-                added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
-                noise_pred = self.unet(
-                    latent_model_input,
-                    t,
-                    encoder_hidden_states=prompt_embeds,
-                    cross_attention_kwargs=cross_attention_kwargs,
-                    added_cond_kwargs=added_cond_kwargs,
-                    return_dict=False,
-                )[0]
-
-                # perform guidance
-                if do_classifier_free_guidance:
-                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
-                    if use_dynamic_threshold:
-                        DynamicThresh = DynThresh(maxSteps=num_inference_steps, experiment_mode=0)
-                        noise_pred = DynamicThresh.dynthresh(noise_pred_text,
-                            noise_pred_uncond,
-                            guidance_scale,
-                            None)
-
-                if do_classifier_free_guidance and guidance_rescale > 0.0:
-                    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
-                    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=guidance_rescale)
-
-                # compute the previous noisy sample x_t -> x_t-1
-                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
-
-                # call the callback, if provided
-                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
-                    progress_bar.update()
-                    if callback is not None and i % callback_steps == 0:
-                        callback(i, t, latents)
-
-        # make sureo the VAE is in float32 mode, as it overflows in float16
-        # torch.cuda.empty_cache()
-        if self.vae.dtype == torch.float16 and self.vae.config.force_upcast:
-            self.upcast_vae()
-            latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)
-
-
-        if not output_type == "latent":
-            latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)
-            image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
-        else:
-            image = latents
-            return StableDiffusionXLPipelineOutput(images=image)
-
-        # image = self.watermark.apply_watermark(image)
-        image = self.image_processor.postprocess(image, output_type=output_type)
-
-        # Offload last model to CPU
-        if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None:
-            self.final_offload_hook.offload()
-
-        if not return_dict:
-            return (image,)
-
-        return StableDiffusionXLPipelineOutput(images=image)
-
-
-if __name__ == "__main__":
-    pass

kolors/pipelines/pipeline_stable_diffusion_xl_chatglm_256_inpainting.py

@@ -1,1790 +0,0 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import inspect
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
-
-import numpy as np
-import PIL.Image
-import torch
-from transformers import (
-    CLIPImageProcessor,
-    CLIPTextModel,
-    CLIPTextModelWithProjection,
-    CLIPTokenizer,
-    CLIPVisionModelWithProjection,
-)
-
-from diffusers.callbacks import MultiPipelineCallbacks, PipelineCallback
-from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
-from diffusers.loaders import (
-    FromSingleFileMixin,
-    IPAdapterMixin,
-    StableDiffusionXLLoraLoaderMixin,
-    TextualInversionLoaderMixin,
-)
-from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
-    XFormersAttnProcessor,
-)
-from diffusers.models.lora import adjust_lora_scale_text_encoder
-from diffusers.schedulers import KarrasDiffusionSchedulers
-from diffusers.utils import (
-    USE_PEFT_BACKEND,
-    deprecate,
-    is_invisible_watermark_available,
-    is_torch_xla_available,
-    logging,
-    replace_example_docstring,
-    scale_lora_layers,
-    unscale_lora_layers,
-)
-from diffusers.utils.torch_utils import randn_tensor
-from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
-
-
-if is_invisible_watermark_available():
-    from diffusers.pipelines.stable_diffusion_xl.watermark import StableDiffusionXLWatermarker
-
-if is_torch_xla_available():
-    import torch_xla.core.xla_model as xm
-
-    XLA_AVAILABLE = True
-else:
-    XLA_AVAILABLE = False
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-EXAMPLE_DOC_STRING = """
-    Examples:
-        ```py
-        >>> import torch
-        >>> from diffusers import StableDiffusionXLInpaintPipeline
-        >>> from diffusers.utils import load_image
-
-        >>> pipe = StableDiffusionXLInpaintPipeline.from_pretrained(
-        ...     "stabilityai/stable-diffusion-xl-base-1.0",
-        ...     torch_dtype=torch.float16,
-        ...     variant="fp16",
-        ...     use_safetensors=True,
-        ... )
-        >>> pipe.to("cuda")
-
-        >>> img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
-        >>> mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
-
-        >>> init_image = load_image(img_url).convert("RGB")
-        >>> mask_image = load_image(mask_url).convert("RGB")
-
-        >>> prompt = "A majestic tiger sitting on a bench"
-        >>> image = pipe(
-        ...     prompt=prompt, image=init_image, mask_image=mask_image, num_inference_steps=50, strength=0.80
-        ... ).images[0]
-        ```
-"""
-
-
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.rescale_noise_cfg
-def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
-    """
-    Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and
-    Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf). See Section 3.4
-    """
-    std_text = noise_pred_text.std(dim=list(range(1, noise_pred_text.ndim)), keepdim=True)
-    std_cfg = noise_cfg.std(dim=list(range(1, noise_cfg.ndim)), keepdim=True)
-    # rescale the results from guidance (fixes overexposure)
-    noise_pred_rescaled = noise_cfg * (std_text / std_cfg)
-    # mix with the original results from guidance by factor guidance_rescale to avoid "plain looking" images
-    noise_cfg = guidance_rescale * noise_pred_rescaled + (1 - guidance_rescale) * noise_cfg
-    return noise_cfg
-
-
-def mask_pil_to_torch(mask, height, width):
-    # preprocess mask
-    if isinstance(mask, (PIL.Image.Image, np.ndarray)):
-        mask = [mask]
-
-    if isinstance(mask, list) and isinstance(mask[0], PIL.Image.Image):
-        mask = [i.resize((width, height), resample=PIL.Image.LANCZOS) for i in mask]
-        mask = np.concatenate([np.array(m.convert("L"))[None, None, :] for m in mask], axis=0)
-        mask = mask.astype(np.float32) / 255.0
-    elif isinstance(mask, list) and isinstance(mask[0], np.ndarray):
-        mask = np.concatenate([m[None, None, :] for m in mask], axis=0)
-
-    mask = torch.from_numpy(mask)
-    return mask
-
-
-def prepare_mask_and_masked_image(image, mask, height, width, return_image: bool = False):
-    """
-    Prepares a pair (image, mask) to be consumed by the Stable Diffusion pipeline. This means that those inputs will be
-    converted to ``torch.Tensor`` with shapes ``batch x channels x height x width`` where ``channels`` is ``3`` for the
-    ``image`` and ``1`` for the ``mask``.
-
-    The ``image`` will be converted to ``torch.float32`` and normalized to be in ``[-1, 1]``. The ``mask`` will be
-    binarized (``mask > 0.5``) and cast to ``torch.float32`` too.
-
-    Args:
-        image (Union[np.array, PIL.Image, torch.Tensor]): The image to inpaint.
-            It can be a ``PIL.Image``, or a ``height x width x 3`` ``np.array`` or a ``channels x height x width``
-            ``torch.Tensor`` or a ``batch x channels x height x width`` ``torch.Tensor``.
-        mask (_type_): The mask to apply to the image, i.e. regions to inpaint.
-            It can be a ``PIL.Image``, or a ``height x width`` ``np.array`` or a ``1 x height x width``
-            ``torch.Tensor`` or a ``batch x 1 x height x width`` ``torch.Tensor``.
-
-
-    Raises:
-        ValueError: ``torch.Tensor`` images should be in the ``[-1, 1]`` range. ValueError: ``torch.Tensor`` mask
-        should be in the ``[0, 1]`` range. ValueError: ``mask`` and ``image`` should have the same spatial dimensions.
-        TypeError: ``mask`` is a ``torch.Tensor`` but ``image`` is not
-            (ot the other way around).
-
-    Returns:
-        tuple[torch.Tensor]: The pair (mask, masked_image) as ``torch.Tensor`` with 4
-            dimensions: ``batch x channels x height x width``.
-    """
-
-    # checkpoint. TOD(Yiyi) - need to clean this up later
-    deprecation_message = "The prepare_mask_and_masked_image method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead"
-    deprecate(
-        "prepare_mask_and_masked_image",
-        "0.30.0",
-        deprecation_message,
-    )
-    if image is None:
-        raise ValueError("`image` input cannot be undefined.")
-
-    if mask is None:
-        raise ValueError("`mask_image` input cannot be undefined.")
-
-    if isinstance(image, torch.Tensor):
-        if not isinstance(mask, torch.Tensor):
-            mask = mask_pil_to_torch(mask, height, width)
-
-        if image.ndim == 3:
-            image = image.unsqueeze(0)
-
-        # Batch and add channel dim for single mask
-        if mask.ndim == 2:
-            mask = mask.unsqueeze(0).unsqueeze(0)
-
-        # Batch single mask or add channel dim
-        if mask.ndim == 3:
-            # Single batched mask, no channel dim or single mask not batched but channel dim
-            if mask.shape[0] == 1:
-                mask = mask.unsqueeze(0)
-
-            # Batched masks no channel dim
-            else:
-                mask = mask.unsqueeze(1)
-
-        assert image.ndim == 4 and mask.ndim == 4, "Image and Mask must have 4 dimensions"
-        # assert image.shape[-2:] == mask.shape[-2:], "Image and Mask must have the same spatial dimensions"
-        assert image.shape[0] == mask.shape[0], "Image and Mask must have the same batch size"
-
-        # Check image is in [-1, 1]
-        # if image.min() < -1 or image.max() > 1:
-        #    raise ValueError("Image should be in [-1, 1] range")
-
-        # Check mask is in [0, 1]
-        if mask.min() < 0 or mask.max() > 1:
-            raise ValueError("Mask should be in [0, 1] range")
-
-        # Binarize mask
-        mask[mask < 0.5] = 0
-        mask[mask >= 0.5] = 1
-
-        # Image as float32
-        image = image.to(dtype=torch.float32)
-    elif isinstance(mask, torch.Tensor):
-        raise TypeError(f"`mask` is a torch.Tensor but `image` (type: {type(image)} is not")
-    else:
-        # preprocess image
-        if isinstance(image, (PIL.Image.Image, np.ndarray)):
-            image = [image]
-        if isinstance(image, list) and isinstance(image[0], PIL.Image.Image):
-            # resize all images w.r.t passed height an width
-            image = [i.resize((width, height), resample=PIL.Image.LANCZOS) for i in image]
-            image = [np.array(i.convert("RGB"))[None, :] for i in image]
-            image = np.concatenate(image, axis=0)
-        elif isinstance(image, list) and isinstance(image[0], np.ndarray):
-            image = np.concatenate([i[None, :] for i in image], axis=0)
-
-        image = image.transpose(0, 3, 1, 2)
-        image = torch.from_numpy(image).to(dtype=torch.float32) / 127.5 - 1.0
-
-        mask = mask_pil_to_torch(mask, height, width)
-        mask[mask < 0.5] = 0
-        mask[mask >= 0.5] = 1
-
-    if image.shape[1] == 4:
-        # images are in latent space and thus can't
-        # be masked set masked_image to None
-        # we assume that the checkpoint is not an inpainting
-        # checkpoint. TOD(Yiyi) - need to clean this up later
-        masked_image = None
-    else:
-        masked_image = image * (mask < 0.5)
-
-    # n.b. ensure backwards compatibility as old function does not return image
-    if return_image:
-        return mask, masked_image, image
-
-    return mask, masked_image
-
-
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.retrieve_latents
-def retrieve_latents(
-    encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample"
-):
-    if hasattr(encoder_output, "latent_dist") and sample_mode == "sample":
-        return encoder_output.latent_dist.sample(generator)
-    elif hasattr(encoder_output, "latent_dist") and sample_mode == "argmax":
-        return encoder_output.latent_dist.mode()
-    elif hasattr(encoder_output, "latents"):
-        return encoder_output.latents
-    else:
-        raise AttributeError("Could not access latents of provided encoder_output")
-
-
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.retrieve_timesteps
-def retrieve_timesteps(
-    scheduler,
-    num_inference_steps: Optional[int] = None,
-    device: Optional[Union[str, torch.device]] = None,
-    timesteps: Optional[List[int]] = None,
-    sigmas: Optional[List[float]] = None,
-    **kwargs,
-):
-    """
-    Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles
-    custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`.
-
-    Args:
-        scheduler (`SchedulerMixin`):
-            The scheduler to get timesteps from.
-        num_inference_steps (`int`):
-            The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps`
-            must be `None`.
-        device (`str` or `torch.device`, *optional*):
-            The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
-        timesteps (`List[int]`, *optional*):
-            Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed,
-            `num_inference_steps` and `sigmas` must be `None`.
-        sigmas (`List[float]`, *optional*):
-            Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed,
-            `num_inference_steps` and `timesteps` must be `None`.
-
-    Returns:
-        `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
-        second element is the number of inference steps.
-    """
-    if timesteps is not None and sigmas is not None:
-        raise ValueError("Only one of `timesteps` or `sigmas` can be passed. Please choose one to set custom values")
-    if timesteps is not None:
-        accepts_timesteps = "timesteps" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accepts_timesteps:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" timestep schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    elif sigmas is not None:
-        accept_sigmas = "sigmas" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accept_sigmas:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" sigmas schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(sigmas=sigmas, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    else:
-        scheduler.set_timesteps(num_inference_steps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-    return timesteps, num_inference_steps
-
-
-class StableDiffusionXLInpaintPipeline(
-    DiffusionPipeline,
-    StableDiffusionMixin,
-    TextualInversionLoaderMixin,
-    StableDiffusionXLLoraLoaderMixin,
-    FromSingleFileMixin,
-    IPAdapterMixin,
-):
-    r"""
-    Pipeline for text-to-image generation using Stable Diffusion XL.
-
-    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
-    library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
-
-    The pipeline also inherits the following loading methods:
-        - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
-        - [`~loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
-        - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
-
-    Args:
-        vae ([`AutoencoderKL`]):
-            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
-        text_encoder ([`CLIPTextModel`]):
-            Frozen text-encoder. Stable Diffusion XL uses the text portion of
-            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel), specifically
-            the [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) variant.
-        text_encoder_2 ([` CLIPTextModelWithProjection`]):
-            Second frozen text-encoder. Stable Diffusion XL uses the text and pool portion of
-            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModelWithProjection),
-            specifically the
-            [laion/CLIP-ViT-bigG-14-laion2B-39B-b160k](https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k)
-            variant.
-        tokenizer (`CLIPTokenizer`):
-            Tokenizer of class
-            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
-        tokenizer_2 (`CLIPTokenizer`):
-            Second Tokenizer of class
-            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
-        unet ([`UNet2DConditionModel`]): Conditional U-Net architecture to denoise the encoded image latents.
-        scheduler ([`SchedulerMixin`]):
-            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
-            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
-        requires_aesthetics_score (`bool`, *optional*, defaults to `"False"`):
-            Whether the `unet` requires a aesthetic_score condition to be passed during inference. Also see the config
-            of `stabilityai/stable-diffusion-xl-refiner-1-0`.
-        force_zeros_for_empty_prompt (`bool`, *optional*, defaults to `"True"`):
-            Whether the negative prompt embeddings shall be forced to always be set to 0. Also see the config of
-            `stabilityai/stable-diffusion-xl-base-1-0`.
-        add_watermarker (`bool`, *optional*):
-            Whether to use the [invisible_watermark library](https://github.com/ShieldMnt/invisible-watermark/) to
-            watermark output images. If not defined, it will default to True if the package is installed, otherwise no
-            watermarker will be used.
-    """
-
-    model_cpu_offload_seq = "text_encoder->text_encoder_2->image_encoder->unet->vae"
-
-    _optional_components = [
-        "tokenizer",
-        "tokenizer_2",
-        "text_encoder",
-        "text_encoder_2",
-        "image_encoder",
-        "feature_extractor",
-    ]
-    _callback_tensor_inputs = [
-        "latents",
-        "prompt_embeds",
-        "negative_prompt_embeds",
-        "add_text_embeds",
-        "add_time_ids",
-        "negative_pooled_prompt_embeds",
-        "add_neg_time_ids",
-        "mask",
-        "masked_image_latents",
-    ]
-
-    def __init__(
-        self,
-        vae: AutoencoderKL,
-        text_encoder: CLIPTextModel,
-        tokenizer: CLIPTokenizer,
-        unet: UNet2DConditionModel,
-        scheduler: KarrasDiffusionSchedulers,
-        tokenizer_2: CLIPTokenizer = None,
-        text_encoder_2: CLIPTextModelWithProjection = None,
-        image_encoder: CLIPVisionModelWithProjection = None,
-        feature_extractor: CLIPImageProcessor = None,
-        requires_aesthetics_score: bool = False,
-        force_zeros_for_empty_prompt: bool = True,
-        add_watermarker: Optional[bool] = None,
-    ):
-        super().__init__()
-
-        self.register_modules(
-            vae=vae,
-            text_encoder=text_encoder,
-            text_encoder_2=text_encoder_2,
-            tokenizer=tokenizer,
-            tokenizer_2=tokenizer_2,
-            unet=unet,
-            image_encoder=image_encoder,
-            feature_extractor=feature_extractor,
-            scheduler=scheduler,
-        )
-        self.register_to_config(force_zeros_for_empty_prompt=force_zeros_for_empty_prompt)
-        self.register_to_config(requires_aesthetics_score=requires_aesthetics_score)
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
-        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
-        self.mask_processor = VaeImageProcessor(
-            vae_scale_factor=self.vae_scale_factor, do_normalize=False, do_binarize=True, do_convert_grayscale=True
-        )
-
-        add_watermarker = add_watermarker if add_watermarker is not None else is_invisible_watermark_available()
-
-        if add_watermarker:
-            self.watermark = StableDiffusionXLWatermarker()
-        else:
-            self.watermark = None
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
-    def encode_image(self, image, device, num_images_per_prompt, output_hidden_states=None):
-        dtype = next(self.image_encoder.parameters()).dtype
-
-        if not isinstance(image, torch.Tensor):
-            image = self.feature_extractor(image, return_tensors="pt").pixel_values
-
-        image = image.to(device=device, dtype=dtype)
-        if output_hidden_states:
-            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True).hidden_states[-2]
-            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
-            uncond_image_enc_hidden_states = self.image_encoder(
-                torch.zeros_like(image), output_hidden_states=True
-            ).hidden_states[-2]
-            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
-                num_images_per_prompt, dim=0
-            )
-            return image_enc_hidden_states, uncond_image_enc_hidden_states
-        else:
-            image_embeds = self.image_encoder(image).image_embeds
-            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
-            uncond_image_embeds = torch.zeros_like(image_embeds)
-
-            return image_embeds, uncond_image_embeds
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_ip_adapter_image_embeds
-    def prepare_ip_adapter_image_embeds(
-        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
-    ):
-        if ip_adapter_image_embeds is None:
-            if not isinstance(ip_adapter_image, list):
-                ip_adapter_image = [ip_adapter_image]
-
-            if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
-                raise ValueError(
-                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP Adapters."
-                )
-
-            image_embeds = []
-            for single_ip_adapter_image, image_proj_layer in zip(
-                ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
-            ):
-                output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
-                single_image_embeds, single_negative_image_embeds = self.encode_image(
-                    single_ip_adapter_image, device, 1, output_hidden_state
-                )
-                single_image_embeds = torch.stack([single_image_embeds] * num_images_per_prompt, dim=0)
-                single_negative_image_embeds = torch.stack(
-                    [single_negative_image_embeds] * num_images_per_prompt, dim=0
-                )
-
-                if do_classifier_free_guidance:
-                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
-                    single_image_embeds = single_image_embeds.to(device)
-
-                image_embeds.append(single_image_embeds)
-        else:
-            repeat_dims = [1]
-            image_embeds = []
-            for single_image_embeds in ip_adapter_image_embeds:
-                if do_classifier_free_guidance:
-                    single_negative_image_embeds, single_image_embeds = single_image_embeds.chunk(2)
-                    single_image_embeds = single_image_embeds.repeat(
-                        num_images_per_prompt, *(repeat_dims * len(single_image_embeds.shape[1:]))
-                    )
-                    single_negative_image_embeds = single_negative_image_embeds.repeat(
-                        num_images_per_prompt, *(repeat_dims * len(single_negative_image_embeds.shape[1:]))
-                    )
-                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
-                else:
-                    single_image_embeds = single_image_embeds.repeat(
-                        num_images_per_prompt, *(repeat_dims * len(single_image_embeds.shape[1:]))
-                    )
-                image_embeds.append(single_image_embeds)
-
-        return image_embeds
-
-    def encode_prompt( 
-        self,
-        prompt,
-        device: Optional[torch.device] = None,
-        num_images_per_prompt: int = 1,
-        do_classifier_free_guidance: bool = True,
-        negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        lora_scale: Optional[float] = None,
-    ):
-        r"""
-        Encodes the prompt into text encoder hidden states.
-
-        Args:
-             prompt (`str` or `List[str]`, *optional*):
-                prompt to be encoded
-            device: (`torch.device`):
-                torch device
-            num_images_per_prompt (`int`):
-                number of images that should be generated per prompt
-            do_classifier_free_guidance (`bool`):
-                whether to use classifier free guidance or not
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
-                If not provided, pooled text embeddings will be generated from `prompt` input argument.
-            negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
-                input argument.
-            lora_scale (`float`, *optional*):
-                A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
-        """
-        # from IPython import embed; embed(); exit()
-        device = device or self._execution_device
-
-        # set lora scale so that monkey patched LoRA
-        # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
-            self._lora_scale = lora_scale
-
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        # Define tokenizers and text encoders
-        tokenizers = [self.tokenizer]
-        text_encoders = [self.text_encoder]
-
-        if prompt_embeds is None:
-            # textual inversion: procecss multi-vector tokens if necessary
-            prompt_embeds_list = []
-            for tokenizer, text_encoder in zip(tokenizers, text_encoders):
-                if isinstance(self, TextualInversionLoaderMixin):
-                    prompt = self.maybe_convert_prompt(prompt, tokenizer)
-
-                text_inputs = tokenizer(
-                    prompt,
-                    padding="max_length",
-                    max_length=256,
-                    truncation=True,
-                    return_tensors="pt",
-                ).to('cuda')
-                output = text_encoder(
-                        input_ids=text_inputs['input_ids'] ,
-                        attention_mask=text_inputs['attention_mask'],
-                        position_ids=text_inputs['position_ids'],
-                        output_hidden_states=True)
-                prompt_embeds = output.hidden_states[-2].permute(1, 0, 2).clone()
-                text_proj = output.hidden_states[-1][-1, :, :].clone()
-                bs_embed, seq_len, _ = prompt_embeds.shape
-                prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
-                prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)
-                prompt_embeds_list.append(prompt_embeds)
-
-            prompt_embeds = prompt_embeds_list[0]
-
-        # get unconditional embeddings for classifier free guidance
-        zero_out_negative_prompt = negative_prompt is None and self.config.force_zeros_for_empty_prompt
-        if do_classifier_free_guidance and negative_prompt_embeds is None and zero_out_negative_prompt:
-            negative_prompt_embeds = torch.zeros_like(prompt_embeds)
-            negative_pooled_prompt_embeds = torch.zeros_like(pooled_prompt_embeds)
-        elif do_classifier_free_guidance and negative_prompt_embeds is None:
-            # negative_prompt = negative_prompt or ""
-            uncond_tokens: List[str]
-            if negative_prompt is None:
-                uncond_tokens = [""] * batch_size
-            elif prompt is not None and type(prompt) is not type(negative_prompt):
-                raise TypeError(
-                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
-                    f" {type(prompt)}."
-                )
-            elif isinstance(negative_prompt, str):
-                uncond_tokens = [negative_prompt]
-            elif batch_size != len(negative_prompt):
-                raise ValueError(
-                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
-                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
-                    " the batch size of `prompt`."
-                )
-            else:
-                uncond_tokens = negative_prompt
-
-            negative_prompt_embeds_list = []
-            for tokenizer, text_encoder in zip(tokenizers, text_encoders):
-                # textual inversion: procecss multi-vector tokens if necessary
-                if isinstance(self, TextualInversionLoaderMixin):
-                    uncond_tokens = self.maybe_convert_prompt(uncond_tokens, tokenizer)
-
-                max_length = prompt_embeds.shape[1]
-                uncond_input = tokenizer(
-                    uncond_tokens,
-                    padding="max_length",
-                    max_length=max_length,
-                    truncation=True,
-                    return_tensors="pt",
-                ).to('cuda')
-                output = text_encoder(
-                        input_ids=uncond_input['input_ids'] ,
-                        attention_mask=uncond_input['attention_mask'],
-                        position_ids=uncond_input['position_ids'],
-                        output_hidden_states=True)
-                negative_prompt_embeds = output.hidden_states[-2].permute(1, 0, 2).clone()
-                negative_text_proj = output.hidden_states[-1][-1, :, :].clone()
-
-                if do_classifier_free_guidance:
-                    # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
-                    seq_len = negative_prompt_embeds.shape[1]
-
-                    negative_prompt_embeds = negative_prompt_embeds.to(dtype=text_encoder.dtype, device=device)
-
-                    negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
-                    negative_prompt_embeds = negative_prompt_embeds.view(
-                        batch_size * num_images_per_prompt, seq_len, -1
-                    )
-
-                    # For classifier free guidance, we need to do two forward passes.
-                    # Here we concatenate the unconditional and text embeddings into a single batch
-                    # to avoid doing two forward passes
-
-                negative_prompt_embeds_list.append(negative_prompt_embeds)
-
-            negative_prompt_embeds = negative_prompt_embeds_list[0]
-
-        bs_embed = text_proj.shape[0]
-        text_proj = text_proj.repeat(1, num_images_per_prompt).view(
-            bs_embed * num_images_per_prompt, -1
-        )
-        negative_text_proj = negative_text_proj.repeat(1, num_images_per_prompt).view(
-            bs_embed * num_images_per_prompt, -1
-        )
-
-        return prompt_embeds, negative_prompt_embeds, text_proj, negative_text_proj
-        
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
-    def prepare_extra_step_kwargs(self, generator, eta):
-        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
-        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
-        # and should be between [0, 1]
-
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        # check if the scheduler accepts generator
-        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        if accepts_generator:
-            extra_step_kwargs["generator"] = generator
-        return extra_step_kwargs
-
-    def check_inputs(
-        self,
-        prompt,
-        prompt_2,
-        image,
-        mask_image,
-        height,
-        width,
-        strength,
-        callback_steps,
-        output_type,
-        negative_prompt=None,
-        negative_prompt_2=None,
-        prompt_embeds=None,
-        negative_prompt_embeds=None,
-        ip_adapter_image=None,
-        ip_adapter_image_embeds=None,
-        callback_on_step_end_tensor_inputs=None,
-        padding_mask_crop=None,
-    ):
-        if strength < 0 or strength > 1:
-            raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")
-
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
-
-        if callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0):
-            raise ValueError(
-                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
-                f" {type(callback_steps)}."
-            )
-
-        if callback_on_step_end_tensor_inputs is not None and not all(
-            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
-        ):
-            raise ValueError(
-                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"
-            )
-
-        if prompt is not None and prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
-                " only forward one of the two."
-            )
-        elif prompt_2 is not None and prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `prompt_2`: {prompt_2} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
-                " only forward one of the two."
-            )
-        elif prompt is None and prompt_embeds is None:
-            raise ValueError(
-                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
-            )
-        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
-            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
-        elif prompt_2 is not None and (not isinstance(prompt_2, str) and not isinstance(prompt_2, list)):
-            raise ValueError(f"`prompt_2` has to be of type `str` or `list` but is {type(prompt_2)}")
-
-        if negative_prompt is not None and negative_prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
-                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
-            )
-        elif negative_prompt_2 is not None and negative_prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `negative_prompt_2`: {negative_prompt_2} and `negative_prompt_embeds`:"
-                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
-            )
-
-        if prompt_embeds is not None and negative_prompt_embeds is not None:
-            if prompt_embeds.shape != negative_prompt_embeds.shape:
-                raise ValueError(
-                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
-                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
-                    f" {negative_prompt_embeds.shape}."
-                )
-        if padding_mask_crop is not None:
-            if not isinstance(image, PIL.Image.Image):
-                raise ValueError(
-                    f"The image should be a PIL image when inpainting mask crop, but is of type" f" {type(image)}."
-                )
-            if not isinstance(mask_image, PIL.Image.Image):
-                raise ValueError(
-                    f"The mask image should be a PIL image when inpainting mask crop, but is of type"
-                    f" {type(mask_image)}."
-                )
-            if output_type != "pil":
-                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is" f" {output_type}.")
-
-        if ip_adapter_image is not None and ip_adapter_image_embeds is not None:
-            raise ValueError(
-                "Provide either `ip_adapter_image` or `ip_adapter_image_embeds`. Cannot leave both `ip_adapter_image` and `ip_adapter_image_embeds` defined."
-            )
-
-        if ip_adapter_image_embeds is not None:
-            if not isinstance(ip_adapter_image_embeds, list):
-                raise ValueError(
-                    f"`ip_adapter_image_embeds` has to be of type `list` but is {type(ip_adapter_image_embeds)}"
-                )
-            elif ip_adapter_image_embeds[0].ndim not in [3, 4]:
-                raise ValueError(
-                    f"`ip_adapter_image_embeds` has to be a list of 3D or 4D tensors but is {ip_adapter_image_embeds[0].ndim}D"
-                )
-
-    def prepare_latents(
-        self,
-        batch_size,
-        num_channels_latents,
-        height,
-        width,
-        dtype,
-        device,
-        generator,
-        latents=None,
-        image=None,
-        timestep=None,
-        is_strength_max=True,
-        add_noise=True,
-        return_noise=False,
-        return_image_latents=False,
-    ):
-        shape = (
-            batch_size,
-            num_channels_latents,
-            int(height) // self.vae_scale_factor,
-            int(width) // self.vae_scale_factor,
-        )
-        if isinstance(generator, list) and len(generator) != batch_size:
-            raise ValueError(
-                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
-                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
-            )
-
-        if (image is None or timestep is None) and not is_strength_max:
-            raise ValueError(
-                "Since strength < 1. initial latents are to be initialised as a combination of Image + Noise."
-                "However, either the image or the noise timestep has not been provided."
-            )
-
-        if image.shape[1] == 4:
-            image_latents = image.to(device=device, dtype=dtype)
-            image_latents = image_latents.repeat(batch_size // image_latents.shape[0], 1, 1, 1)
-        elif return_image_latents or (latents is None and not is_strength_max):
-            image = image.to(device=device, dtype=dtype)
-            image_latents = self._encode_vae_image(image=image, generator=generator)
-            image_latents = image_latents.repeat(batch_size // image_latents.shape[0], 1, 1, 1)
-
-        if latents is None and add_noise:
-            noise = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-            # if strength is 1. then initialise the latents to noise, else initial to image + noise
-            latents = noise if is_strength_max else self.scheduler.add_noise(image_latents, noise, timestep)
-            # if pure noise then scale the initial latents by the  Scheduler's init sigma
-            latents = latents * self.scheduler.init_noise_sigma if is_strength_max else latents
-        elif add_noise:
-            noise = latents.to(device)
-            latents = noise * self.scheduler.init_noise_sigma
-        else:
-            noise = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-            latents = image_latents.to(device)
-
-        outputs = (latents,)
-
-        if return_noise:
-            outputs += (noise,)
-
-        if return_image_latents:
-            outputs += (image_latents,)
-
-        return outputs
-
-    def _encode_vae_image(self, image: torch.Tensor, generator: torch.Generator):
-        dtype = image.dtype
-        if self.vae.config.force_upcast:
-            image = image.float()
-            self.vae.to(dtype=torch.float32)
-
-        if isinstance(generator, list):
-            image_latents = [
-                retrieve_latents(self.vae.encode(image[i : i + 1]), generator=generator[i])
-                for i in range(image.shape[0])
-            ]
-            image_latents = torch.cat(image_latents, dim=0)
-        else:
-            image_latents = retrieve_latents(self.vae.encode(image), generator=generator)
-
-        if self.vae.config.force_upcast:
-            self.vae.to(dtype)
-
-        image_latents = image_latents.to(dtype)
-        image_latents = self.vae.config.scaling_factor * image_latents
-
-        return image_latents
-
-    def prepare_mask_latents(
-        self, mask, masked_image, batch_size, height, width, dtype, device, generator, do_classifier_free_guidance
-    ):
-        # resize the mask to latents shape as we concatenate the mask to the latents
-        # we do that before converting to dtype to avoid breaking in case we're using cpu_offload
-        # and half precision
-        mask = torch.nn.functional.interpolate(
-            mask, size=(height // self.vae_scale_factor, width // self.vae_scale_factor)
-        )
-        mask = mask.to(device=device, dtype=dtype)
-
-        # duplicate mask and masked_image_latents for each generation per prompt, using mps friendly method
-        if mask.shape[0] < batch_size:
-            if not batch_size % mask.shape[0] == 0:
-                raise ValueError(
-                    "The passed mask and the required batch size don't match. Masks are supposed to be duplicated to"
-                    f" a total batch size of {batch_size}, but {mask.shape[0]} masks were passed. Make sure the number"
-                    " of masks that you pass is divisible by the total requested batch size."
-                )
-            mask = mask.repeat(batch_size // mask.shape[0], 1, 1, 1)
-
-        mask = torch.cat([mask] * 2) if do_classifier_free_guidance else mask
-
-        if masked_image is not None and masked_image.shape[1] == 4:
-            masked_image_latents = masked_image
-        else:
-            masked_image_latents = None
-
-        if masked_image is not None:
-            if masked_image_latents is None:
-                masked_image = masked_image.to(device=device, dtype=dtype)
-                masked_image_latents = self._encode_vae_image(masked_image, generator=generator)
-
-            if masked_image_latents.shape[0] < batch_size:
-                if not batch_size % masked_image_latents.shape[0] == 0:
-                    raise ValueError(
-                        "The passed images and the required batch size don't match. Images are supposed to be duplicated"
-                        f" to a total batch size of {batch_size}, but {masked_image_latents.shape[0]} images were passed."
-                        " Make sure the number of images that you pass is divisible by the total requested batch size."
-                    )
-                masked_image_latents = masked_image_latents.repeat(
-                    batch_size // masked_image_latents.shape[0], 1, 1, 1
-                )
-
-            masked_image_latents = (
-                torch.cat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
-            )
-
-            # aligning device to prevent device errors when concating it with the latent model input
-            masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
-
-        return mask, masked_image_latents
-
-    # Copied from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl_img2img.StableDiffusionXLImg2ImgPipeline.get_timesteps
-    def get_timesteps(self, num_inference_steps, strength, device, denoising_start=None):
-        # get the original timestep using init_timestep
-        if denoising_start is None:
-            init_timestep = min(int(num_inference_steps * strength), num_inference_steps)
-            t_start = max(num_inference_steps - init_timestep, 0)
-        else:
-            t_start = 0
-
-        timesteps = self.scheduler.timesteps[t_start * self.scheduler.order :]
-
-        # Strength is irrelevant if we directly request a timestep to start at;
-        # that is, strength is determined by the denoising_start instead.
-        if denoising_start is not None:
-            discrete_timestep_cutoff = int(
-                round(
-                    self.scheduler.config.num_train_timesteps
-                    - (denoising_start * self.scheduler.config.num_train_timesteps)
-                )
-            )
-
-            num_inference_steps = (timesteps < discrete_timestep_cutoff).sum().item()
-            if self.scheduler.order == 2 and num_inference_steps % 2 == 0:
-                # if the scheduler is a 2nd order scheduler we might have to do +1
-                # because `num_inference_steps` might be even given that every timestep
-                # (except the highest one) is duplicated. If `num_inference_steps` is even it would
-                # mean that we cut the timesteps in the middle of the denoising step
-                # (between 1st and 2nd derivative) which leads to incorrect results. By adding 1
-                # we ensure that the denoising process always ends after the 2nd derivate step of the scheduler
-                num_inference_steps = num_inference_steps + 1
-
-            # because t_n+1 >= t_n, we slice the timesteps starting from the end
-            timesteps = timesteps[-num_inference_steps:]
-            return timesteps, num_inference_steps
-
-        return timesteps, num_inference_steps - t_start
-
-    # Copied from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl_img2img.StableDiffusionXLImg2ImgPipeline._get_add_time_ids
-    def _get_add_time_ids(
-        self,
-        original_size,
-        crops_coords_top_left,
-        target_size,
-        aesthetic_score,
-        negative_aesthetic_score,
-        negative_original_size,
-        negative_crops_coords_top_left,
-        negative_target_size,
-        dtype,
-        text_encoder_projection_dim=None,
-    ):
-        if self.config.requires_aesthetics_score:
-            add_time_ids = list(original_size + crops_coords_top_left + (aesthetic_score,))
-            add_neg_time_ids = list(
-                negative_original_size + negative_crops_coords_top_left + (negative_aesthetic_score,)
-            )
-        else:
-            add_time_ids = list(original_size + crops_coords_top_left + target_size)
-            add_neg_time_ids = list(negative_original_size + crops_coords_top_left + negative_target_size)
-
-        passed_add_embed_dim = (
-            self.unet.config.addition_time_embed_dim * len(add_time_ids) + 4096
-        )
-        expected_add_embed_dim = self.unet.add_embedding.linear_1.in_features
-
-        if (
-            expected_add_embed_dim > passed_add_embed_dim
-            and (expected_add_embed_dim - passed_add_embed_dim) == self.unet.config.addition_time_embed_dim
-        ):
-            raise ValueError(
-                f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. Please make sure to enable `requires_aesthetics_score` with `pipe.register_to_config(requires_aesthetics_score=True)` to make sure `aesthetic_score` {aesthetic_score} and `negative_aesthetic_score` {negative_aesthetic_score} is correctly used by the model."
-            )
-        elif (
-            expected_add_embed_dim < passed_add_embed_dim
-            and (passed_add_embed_dim - expected_add_embed_dim) == self.unet.config.addition_time_embed_dim
-        ):
-            raise ValueError(
-                f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. Please make sure to disable `requires_aesthetics_score` with `pipe.register_to_config(requires_aesthetics_score=False)` to make sure `target_size` {target_size} is correctly used by the model."
-            )
-        elif expected_add_embed_dim != passed_add_embed_dim:
-            raise ValueError(
-                f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. The model has an incorrect config. Please check `unet.config.time_embedding_type` and `text_encoder_2.config.projection_dim`."
-            )
-
-        add_time_ids = torch.tensor([add_time_ids], dtype=dtype)
-        add_neg_time_ids = torch.tensor([add_neg_time_ids], dtype=dtype)
-
-        return add_time_ids, add_neg_time_ids
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
-    def upcast_vae(self):
-        dtype = self.vae.dtype
-        self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
-
-    # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
-    def get_guidance_scale_embedding(
-        self, w: torch.Tensor, embedding_dim: int = 512, dtype: torch.dtype = torch.float32
-    ) -> torch.Tensor:
-        """
-        See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298
-
-        Args:
-            w (`torch.Tensor`):
-                Generate embedding vectors with a specified guidance scale to subsequently enrich timestep embeddings.
-            embedding_dim (`int`, *optional*, defaults to 512):
-                Dimension of the embeddings to generate.
-            dtype (`torch.dtype`, *optional*, defaults to `torch.float32`):
-                Data type of the generated embeddings.
-
-        Returns:
-            `torch.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
-        """
-        assert len(w.shape) == 1
-        w = w * 1000.0
-
-        half_dim = embedding_dim // 2
-        emb = torch.log(torch.tensor(10000.0)) / (half_dim - 1)
-        emb = torch.exp(torch.arange(half_dim, dtype=dtype) * -emb)
-        emb = w.to(dtype)[:, None] * emb[None, :]
-        emb = torch.cat([torch.sin(emb), torch.cos(emb)], dim=1)
-        if embedding_dim % 2 == 1:  # zero pad
-            emb = torch.nn.functional.pad(emb, (0, 1))
-        assert emb.shape == (w.shape[0], embedding_dim)
-        return emb
-
-    @property
-    def guidance_scale(self):
-        return self._guidance_scale
-
-    @property
-    def guidance_rescale(self):
-        return self._guidance_rescale
-
-    @property
-    def clip_skip(self):
-        return self._clip_skip
-
-    # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
-    # corresponds to doing no classifier free guidance.
-    @property
-    def do_classifier_free_guidance(self):
-        return self._guidance_scale > 1 and self.unet.config.time_cond_proj_dim is None
-
-    @property
-    def cross_attention_kwargs(self):
-        return self._cross_attention_kwargs
-
-    @property
-    def denoising_end(self):
-        return self._denoising_end
-
-    @property
-    def denoising_start(self):
-        return self._denoising_start
-
-    @property
-    def num_timesteps(self):
-        return self._num_timesteps
-
-    @property
-    def interrupt(self):
-        return self._interrupt
-
-    @torch.no_grad()
-    @replace_example_docstring(EXAMPLE_DOC_STRING)
-    def __call__(
-        self,
-        prompt: Union[str, List[str]] = None,
-        prompt_2: Optional[Union[str, List[str]]] = None,
-        image: PipelineImageInput = None,
-        mask_image: PipelineImageInput = None,
-        masked_image_latents: torch.Tensor = None,
-        height: Optional[int] = None,
-        width: Optional[int] = None,
-        padding_mask_crop: Optional[int] = None,
-        strength: float = 0.9999,
-        num_inference_steps: int = 50,
-        timesteps: List[int] = None,
-        sigmas: List[float] = None,
-        denoising_start: Optional[float] = None,
-        denoising_end: Optional[float] = None,
-        guidance_scale: float = 7.5,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        negative_prompt_2: Optional[Union[str, List[str]]] = None,
-        num_images_per_prompt: Optional[int] = 1,
-        eta: float = 0.0,
-        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.Tensor] = None,
-        prompt_embeds: Optional[torch.Tensor] = None,
-        negative_prompt_embeds: Optional[torch.Tensor] = None,
-        pooled_prompt_embeds: Optional[torch.Tensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
-        ip_adapter_image: Optional[PipelineImageInput] = None,
-        ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
-        output_type: Optional[str] = "pil",
-        return_dict: bool = True,
-        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-        guidance_rescale: float = 0.0,
-        original_size: Tuple[int, int] = None,
-        crops_coords_top_left: Tuple[int, int] = (0, 0),
-        target_size: Tuple[int, int] = None,
-        negative_original_size: Optional[Tuple[int, int]] = None,
-        negative_crops_coords_top_left: Tuple[int, int] = (0, 0),
-        negative_target_size: Optional[Tuple[int, int]] = None,
-        aesthetic_score: float = 6.0,
-        negative_aesthetic_score: float = 2.5,
-        clip_skip: Optional[int] = None,
-        callback_on_step_end: Optional[
-            Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
-        ] = None,
-        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
-        **kwargs,
-    ):
-        r"""
-        Function invoked when calling the pipeline for generation.
-
-        Args:
-            prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
-                instead.
-            prompt_2 (`str` or `List[str]`, *optional*):
-                The prompt or prompts to be sent to the `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
-                used in both text-encoders
-            image (`PIL.Image.Image`):
-                `Image`, or tensor representing an image batch which will be inpainted, *i.e.* parts of the image will
-                be masked out with `mask_image` and repainted according to `prompt`.
-            mask_image (`PIL.Image.Image`):
-                `Image`, or tensor representing an image batch, to mask `image`. White pixels in the mask will be
-                repainted, while black pixels will be preserved. If `mask_image` is a PIL image, it will be converted
-                to a single channel (luminance) before use. If it's a tensor, it should contain one color channel (L)
-                instead of 3, so the expected shape would be `(B, H, W, 1)`.
-            height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The height in pixels of the generated image. This is set to 1024 by default for the best results.
-                Anything below 512 pixels won't work well for
-                [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
-                and checkpoints that are not specifically fine-tuned on low resolutions.
-            width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The width in pixels of the generated image. This is set to 1024 by default for the best results.
-                Anything below 512 pixels won't work well for
-                [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
-                and checkpoints that are not specifically fine-tuned on low resolutions.
-            padding_mask_crop (`int`, *optional*, defaults to `None`):
-                The size of margin in the crop to be applied to the image and masking. If `None`, no crop is applied to
-                image and mask_image. If `padding_mask_crop` is not `None`, it will first find a rectangular region
-                with the same aspect ration of the image and contains all masked area, and then expand that area based
-                on `padding_mask_crop`. The image and mask_image will then be cropped based on the expanded area before
-                resizing to the original image size for inpainting. This is useful when the masked area is small while
-                the image is large and contain information irrelevant for inpainting, such as background.
-            strength (`float`, *optional*, defaults to 0.9999):
-                Conceptually, indicates how much to transform the masked portion of the reference `image`. Must be
-                between 0 and 1. `image` will be used as a starting point, adding more noise to it the larger the
-                `strength`. The number of denoising steps depends on the amount of noise initially added. When
-                `strength` is 1, added noise will be maximum and the denoising process will run for the full number of
-                iterations specified in `num_inference_steps`. A value of 1, therefore, essentially ignores the masked
-                portion of the reference `image`. Note that in the case of `denoising_start` being declared as an
-                integer, the value of `strength` will be ignored.
-            num_inference_steps (`int`, *optional*, defaults to 50):
-                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
-                expense of slower inference.
-            timesteps (`List[int]`, *optional*):
-                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
-                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
-                passed will be used. Must be in descending order.
-            sigmas (`List[float]`, *optional*):
-                Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
-                their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
-                will be used.
-            denoising_start (`float`, *optional*):
-                When specified, indicates the fraction (between 0.0 and 1.0) of the total denoising process to be
-                bypassed before it is initiated. Consequently, the initial part of the denoising process is skipped and
-                it is assumed that the passed `image` is a partly denoised image. Note that when this is specified,
-                strength will be ignored. The `denoising_start` parameter is particularly beneficial when this pipeline
-                is integrated into a "Mixture of Denoisers" multi-pipeline setup, as detailed in [**Refining the Image
-                Output**](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl#refining-the-image-output).
-            denoising_end (`float`, *optional*):
-                When specified, determines the fraction (between 0.0 and 1.0) of the total denoising process to be
-                completed before it is intentionally prematurely terminated. As a result, the returned sample will
-                still retain a substantial amount of noise (ca. final 20% of timesteps still needed) and should be
-                denoised by a successor pipeline that has `denoising_start` set to 0.8 so that it only denoises the
-                final 20% of the scheduler. The denoising_end parameter should ideally be utilized when this pipeline
-                forms a part of a "Mixture of Denoisers" multi-pipeline setup, as elaborated in [**Refining the Image
-                Output**](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl#refining-the-image-output).
-            guidance_scale (`float`, *optional*, defaults to 7.5):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            negative_prompt_2 (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation to be sent to `tokenizer_2` and
-                `text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
-            prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            pooled_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
-                If not provided, pooled text embeddings will be generated from `prompt` input argument.
-            negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
-                input argument.
-            ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
-            ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
-                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
-                contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
-            num_images_per_prompt (`int`, *optional*, defaults to 1):
-                The number of images to generate per prompt.
-            eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
-                [`schedulers.DDIMScheduler`], will be ignored for others.
-            generator (`torch.Generator`, *optional*):
-                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
-                to make generation deterministic.
-            latents (`torch.Tensor`, *optional*):
-                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
-                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
-                tensor will ge generated by sampling using the supplied random `generator`.
-            output_type (`str`, *optional*, defaults to `"pil"`):
-                The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
-                plain tuple.
-            cross_attention_kwargs (`dict`, *optional*):
-                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
-                `self.processor` in
-                [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
-            original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
-                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
-                explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
-            crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
-                `crops_coords_top_left` can be used to generate an image that appears to be "cropped" from the position
-                `crops_coords_top_left` downwards. Favorable, well-centered images are usually achieved by setting
-                `crops_coords_top_left` to (0, 0). Part of SDXL's micro-conditioning as explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
-            target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                For most cases, `target_size` should be set to the desired height and width of the generated image. If
-                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
-                section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
-            negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                To negatively condition the generation process based on a specific image resolution. Part of SDXL's
-                micro-conditioning as explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
-                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
-            negative_crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
-                To negatively condition the generation process based on a specific crop coordinates. Part of SDXL's
-                micro-conditioning as explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
-                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
-            negative_target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                To negatively condition the generation process based on a target image resolution. It should be as same
-                as the `target_size` for most cases. Part of SDXL's micro-conditioning as explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
-                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
-            aesthetic_score (`float`, *optional*, defaults to 6.0):
-                Used to simulate an aesthetic score of the generated image by influencing the positive text condition.
-                Part of SDXL's micro-conditioning as explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
-            negative_aesthetic_score (`float`, *optional*, defaults to 2.5):
-                Part of SDXL's micro-conditioning as explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). Can be used to
-                simulate an aesthetic score of the generated image by influencing the negative text condition.
-            clip_skip (`int`, *optional*):
-                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
-                the output of the pre-final layer will be used for computing the prompt embeddings.
-            callback_on_step_end (`Callable`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
-                A function or a subclass of `PipelineCallback` or `MultiPipelineCallbacks` that is called at the end of
-                each denoising step during the inference. with the following arguments: `callback_on_step_end(self:
-                DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)`. `callback_kwargs` will include a
-                list of all tensors as specified by `callback_on_step_end_tensor_inputs`.
-            callback_on_step_end_tensor_inputs (`List`, *optional*):
-                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
-                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeline class.
-
-        Examples:
-
-        Returns:
-            [`~pipelines.stable_diffusion.StableDiffusionXLPipelineOutput`] or `tuple`:
-            [`~pipelines.stable_diffusion.StableDiffusionXLPipelineOutput`] if `return_dict` is True, otherwise a
-            `tuple. `tuple. When returning a tuple, the first element is a list with the generated images.
-        """
-
-        callback = kwargs.pop("callback", None)
-        callback_steps = kwargs.pop("callback_steps", None)
-
-        if callback is not None:
-            deprecate(
-                "callback",
-                "1.0.0",
-                "Passing `callback` as an input argument to `__call__` is deprecated, consider use `callback_on_step_end`",
-            )
-        if callback_steps is not None:
-            deprecate(
-                "callback_steps",
-                "1.0.0",
-                "Passing `callback_steps` as an input argument to `__call__` is deprecated, consider use `callback_on_step_end`",
-            )
-
-        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
-            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs
-
-        # 0. Default height and width to unet
-        height = height or self.unet.config.sample_size * self.vae_scale_factor
-        width = width or self.unet.config.sample_size * self.vae_scale_factor
-
-        # 1. Check inputs
-        self.check_inputs(
-            prompt,
-            prompt_2,
-            image,
-            mask_image,
-            height,
-            width,
-            strength,
-            callback_steps,
-            output_type,
-            negative_prompt,
-            negative_prompt_2,
-            prompt_embeds,
-            negative_prompt_embeds,
-            ip_adapter_image,
-            ip_adapter_image_embeds,
-            callback_on_step_end_tensor_inputs,
-            padding_mask_crop,
-        )
-
-        self._guidance_scale = guidance_scale
-        self._guidance_rescale = guidance_rescale
-        self._clip_skip = clip_skip
-        self._cross_attention_kwargs = cross_attention_kwargs
-        self._denoising_end = denoising_end
-        self._denoising_start = denoising_start
-        self._interrupt = False
-
-        # 2. Define call parameters
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        device = self._execution_device
-
-        # 3. Encode input prompt
-        text_encoder_lora_scale = (
-            self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
-        )
-
-        (
-            prompt_embeds,
-            negative_prompt_embeds,
-            pooled_prompt_embeds,
-            negative_pooled_prompt_embeds,
-        ) = self.encode_prompt(
-            prompt=prompt,
-            device=device,
-            num_images_per_prompt=num_images_per_prompt,
-            do_classifier_free_guidance=self.do_classifier_free_guidance,
-            negative_prompt=negative_prompt,
-            prompt_embeds=prompt_embeds,
-            negative_prompt_embeds=negative_prompt_embeds,
-            pooled_prompt_embeds=pooled_prompt_embeds,
-            negative_pooled_prompt_embeds=negative_pooled_prompt_embeds,
-            lora_scale=text_encoder_lora_scale,
-        )
-
-        # 4. set timesteps
-        def denoising_value_valid(dnv):
-            return isinstance(dnv, float) and 0 < dnv < 1
-
-        timesteps, num_inference_steps = retrieve_timesteps(
-            self.scheduler, num_inference_steps, device, timesteps, sigmas
-        )
-        timesteps, num_inference_steps = self.get_timesteps(
-            num_inference_steps,
-            strength,
-            device,
-            denoising_start=self.denoising_start if denoising_value_valid(self.denoising_start) else None,
-        )
-        # check that number of inference steps is not < 1 - as this doesn't make sense
-        if num_inference_steps < 1:
-            raise ValueError(
-                f"After adjusting the num_inference_steps by strength parameter: {strength}, the number of pipeline"
-                f"steps is {num_inference_steps} which is < 1 and not appropriate for this pipeline."
-            )
-        # at which timestep to set the initial noise (n.b. 50% if strength is 0.5)
-        latent_timestep = timesteps[:1].repeat(batch_size * num_images_per_prompt)
-        # create a boolean to check if the strength is set to 1. if so then initialise the latents with pure noise
-        is_strength_max = strength == 1.0
-
-        # 5. Preprocess mask and image
-        if padding_mask_crop is not None:
-            crops_coords = self.mask_processor.get_crop_region(mask_image, width, height, pad=padding_mask_crop)
-            resize_mode = "fill"
-        else:
-            crops_coords = None
-            resize_mode = "default"
-
-        original_image = image
-        init_image = self.image_processor.preprocess(
-            image, height=height, width=width, crops_coords=crops_coords, resize_mode=resize_mode
-        )
-        init_image = init_image.to(dtype=torch.float32)
-
-        mask = self.mask_processor.preprocess(
-            mask_image, height=height, width=width, resize_mode=resize_mode, crops_coords=crops_coords
-        )
-
-        if masked_image_latents is not None:
-            masked_image = masked_image_latents
-        elif init_image.shape[1] == 4:
-            # if images are in latent space, we can't mask it
-            masked_image = None
-        else:
-            masked_image = init_image * (mask < 0.5)
-
-        # 6. Prepare latent variables
-        num_channels_latents = self.vae.config.latent_channels
-        num_channels_unet = self.unet.config.in_channels
-        return_image_latents = num_channels_unet == 4
-
-        add_noise = True if self.denoising_start is None else False
-        latents_outputs = self.prepare_latents(
-            batch_size * num_images_per_prompt,
-            num_channels_latents,
-            height,
-            width,
-            prompt_embeds.dtype,
-            device,
-            generator,
-            latents,
-            image=init_image,
-            timestep=latent_timestep,
-            is_strength_max=is_strength_max,
-            add_noise=add_noise,
-            return_noise=True,
-            return_image_latents=return_image_latents,
-        )
-
-        if return_image_latents:
-            latents, noise, image_latents = latents_outputs
-        else:
-            latents, noise = latents_outputs
-
-        # 7. Prepare mask latent variables
-        mask, masked_image_latents = self.prepare_mask_latents(
-            mask,
-            masked_image,
-            batch_size * num_images_per_prompt,
-            height,
-            width,
-            prompt_embeds.dtype,
-            device,
-            generator,
-            self.do_classifier_free_guidance,
-        )
-
-        # 8. Check that sizes of mask, masked image and latents match
-        if num_channels_unet == 9:
-            # default case for runwayml/stable-diffusion-inpainting
-            num_channels_mask = mask.shape[1]
-            num_channels_masked_image = masked_image_latents.shape[1]
-            if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:
-                raise ValueError(
-                    f"Incorrect configuration settings! The config of `pipeline.unet`: {self.unet.config} expects"
-                    f" {self.unet.config.in_channels} but received `num_channels_latents`: {num_channels_latents} +"
-                    f" `num_channels_mask`: {num_channels_mask} + `num_channels_masked_image`: {num_channels_masked_image}"
-                    f" = {num_channels_latents+num_channels_masked_image+num_channels_mask}. Please verify the config of"
-                    " `pipeline.unet` or your `mask_image` or `image` input."
-                )
-        elif num_channels_unet != 4:
-            raise ValueError(
-                f"The unet {self.unet.__class__} should have either 4 or 9 input channels, not {self.unet.config.in_channels}."
-            )
-        # 8.1 Prepare extra step kwargs.
-        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
-
-        # 9. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
-        height, width = latents.shape[-2:]
-        height = height * self.vae_scale_factor
-        width = width * self.vae_scale_factor
-
-        original_size = original_size or (height, width)
-        target_size = target_size or (height, width)
-
-        # 10. Prepare added time ids & embeddings
-        if negative_original_size is None:
-            negative_original_size = original_size
-        if negative_target_size is None:
-            negative_target_size = target_size
-
-        add_text_embeds = pooled_prompt_embeds
-        if self.text_encoder_2 is None:
-            text_encoder_projection_dim = int(pooled_prompt_embeds.shape[-1])
-        else:
-            text_encoder_projection_dim = self.text_encoder_2.config.projection_dim
-
-        add_time_ids, add_neg_time_ids = self._get_add_time_ids(
-            original_size,
-            crops_coords_top_left,
-            target_size,
-            aesthetic_score,
-            negative_aesthetic_score,
-            negative_original_size,
-            negative_crops_coords_top_left,
-            negative_target_size,
-            dtype=prompt_embeds.dtype,
-            text_encoder_projection_dim=text_encoder_projection_dim,
-        )
-        add_time_ids = add_time_ids.repeat(batch_size * num_images_per_prompt, 1)
-
-        if self.do_classifier_free_guidance:
-            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
-            add_text_embeds = torch.cat([negative_pooled_prompt_embeds, add_text_embeds], dim=0)
-            add_neg_time_ids = add_neg_time_ids.repeat(batch_size * num_images_per_prompt, 1)
-            add_time_ids = torch.cat([add_neg_time_ids, add_time_ids], dim=0)
-
-        prompt_embeds = prompt_embeds.to(device)
-        add_text_embeds = add_text_embeds.to(device)
-        add_time_ids = add_time_ids.to(device)
-
-        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
-            image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image,
-                ip_adapter_image_embeds,
-                device,
-                batch_size * num_images_per_prompt,
-                self.do_classifier_free_guidance,
-            )
-            
-
-        # 11. Denoising loop
-        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
-
-        if (
-            self.denoising_end is not None
-            and self.denoising_start is not None
-            and denoising_value_valid(self.denoising_end)
-            and denoising_value_valid(self.denoising_start)
-            and self.denoising_start >= self.denoising_end
-        ):
-            raise ValueError(
-                f"`denoising_start`: {self.denoising_start} cannot be larger than or equal to `denoising_end`: "
-                + f" {self.denoising_end} when using type float."
-            )
-        elif self.denoising_end is not None and denoising_value_valid(self.denoising_end):
-            discrete_timestep_cutoff = int(
-                round(
-                    self.scheduler.config.num_train_timesteps
-                    - (self.denoising_end * self.scheduler.config.num_train_timesteps)
-                )
-            )
-            num_inference_steps = len(list(filter(lambda ts: ts >= discrete_timestep_cutoff, timesteps)))
-            timesteps = timesteps[:num_inference_steps]
-
-        # 11.1 Optionally get Guidance Scale Embedding
-        timestep_cond = None
-        if self.unet.config.time_cond_proj_dim is not None:
-            guidance_scale_tensor = torch.tensor(self.guidance_scale - 1).repeat(batch_size * num_images_per_prompt)
-            timestep_cond = self.get_guidance_scale_embedding(
-                guidance_scale_tensor, embedding_dim=self.unet.config.time_cond_proj_dim
-            ).to(device=device, dtype=latents.dtype)
-
-        self._num_timesteps = len(timesteps)
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            for i, t in enumerate(timesteps):
-                if self.interrupt:
-                    continue
-                # expand the latents if we are doing classifier free guidance
-                latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
-
-                # concat latents, mask, masked_image_latents in the channel dimension
-                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
-
-                if num_channels_unet == 9:
-                    latent_model_input = torch.cat([latent_model_input, mask, masked_image_latents], dim=1)
-
-                # predict the noise residual
-                added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
-                if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
-                    added_cond_kwargs["image_embeds"] = image_embeds
-                noise_pred = self.unet(
-                    latent_model_input,
-                    t,
-                    encoder_hidden_states=prompt_embeds,
-                    timestep_cond=timestep_cond,
-                    cross_attention_kwargs=self.cross_attention_kwargs,
-                    added_cond_kwargs=added_cond_kwargs,
-                    return_dict=False,
-                )[0]
-
-                # perform guidance
-                if self.do_classifier_free_guidance:
-                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                    noise_pred = noise_pred_uncond + self.guidance_scale * (noise_pred_text - noise_pred_uncond)
-
-                if self.do_classifier_free_guidance and self.guidance_rescale > 0.0:
-                    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
-                    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=self.guidance_rescale)
-
-                # compute the previous noisy sample x_t -> x_t-1
-                latents_dtype = latents.dtype
-                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
-                if latents.dtype != latents_dtype:
-                    if torch.backends.mps.is_available():
-                        # some platforms (eg. apple mps) misbehave due to a pytorch bug: https://github.com/pytorch/pytorch/pull/99272
-                        latents = latents.to(latents_dtype)
-
-                if num_channels_unet == 4:
-                    init_latents_proper = image_latents
-                    if self.do_classifier_free_guidance:
-                        init_mask, _ = mask.chunk(2)
-                    else:
-                        init_mask = mask
-
-                    if i < len(timesteps) - 1:
-                        noise_timestep = timesteps[i + 1]
-                        init_latents_proper = self.scheduler.add_noise(
-                            init_latents_proper, noise, torch.tensor([noise_timestep])
-                        )
-
-                    latents = (1 - init_mask) * init_latents_proper + init_mask * latents
-
-                if callback_on_step_end is not None:
-                    callback_kwargs = {}
-                    for k in callback_on_step_end_tensor_inputs:
-                        callback_kwargs[k] = locals()[k]
-                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)
-
-                    latents = callback_outputs.pop("latents", latents)
-                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
-                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)
-                    add_text_embeds = callback_outputs.pop("add_text_embeds", add_text_embeds)
-                    negative_pooled_prompt_embeds = callback_outputs.pop(
-                        "negative_pooled_prompt_embeds", negative_pooled_prompt_embeds
-                    )
-                    add_time_ids = callback_outputs.pop("add_time_ids", add_time_ids)
-                    add_neg_time_ids = callback_outputs.pop("add_neg_time_ids", add_neg_time_ids)
-                    mask = callback_outputs.pop("mask", mask)
-                    masked_image_latents = callback_outputs.pop("masked_image_latents", masked_image_latents)
-
-                # call the callback, if provided
-                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
-                    progress_bar.update()
-                    if callback is not None and i % callback_steps == 0:
-                        step_idx = i // getattr(self.scheduler, "order", 1)
-                        callback(step_idx, t, latents)
-
-                if XLA_AVAILABLE:
-                    xm.mark_step()
-
-        if not output_type == "latent":
-            # make sure the VAE is in float32 mode, as it overflows in float16
-            needs_upcasting = self.vae.dtype == torch.float16 and self.vae.config.force_upcast
-
-            if needs_upcasting:
-                self.upcast_vae()
-                latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)
-            elif latents.dtype != self.vae.dtype:
-                if torch.backends.mps.is_available():
-                    # some platforms (eg. apple mps) misbehave due to a pytorch bug: https://github.com/pytorch/pytorch/pull/99272
-                    self.vae = self.vae.to(latents.dtype)
-
-            # unscale/denormalize the latents
-            # denormalize with the mean and std if available and not None
-            has_latents_mean = hasattr(self.vae.config, "latents_mean") and self.vae.config.latents_mean is not None
-            has_latents_std = hasattr(self.vae.config, "latents_std") and self.vae.config.latents_std is not None
-            if has_latents_mean and has_latents_std:
-                latents_mean = (
-                    torch.tensor(self.vae.config.latents_mean).view(1, 4, 1, 1).to(latents.device, latents.dtype)
-                )
-                latents_std = (
-                    torch.tensor(self.vae.config.latents_std).view(1, 4, 1, 1).to(latents.device, latents.dtype)
-                )
-                latents = latents * latents_std / self.vae.config.scaling_factor + latents_mean
-            else:
-                latents = latents / self.vae.config.scaling_factor
-
-            image = self.vae.decode(latents, return_dict=False)[0]
-
-            # cast back to fp16 if needed
-            if needs_upcasting:
-                self.vae.to(dtype=torch.float16)
-        else:
-            return StableDiffusionXLPipelineOutput(images=latents)
-
-        # apply watermark if available
-        if self.watermark is not None:
-            image = self.watermark.apply_watermark(image)
-
-        image = self.image_processor.postprocess(image, output_type=output_type)
-
-        if padding_mask_crop is not None:
-            image = [self.image_processor.apply_overlay(mask_image, original_image, i, crops_coords) for i in image]
-
-        # Offload all models
-        self.maybe_free_model_hooks()
-
-        if not return_dict:
-            return (image,)
-
-        return StableDiffusionXLPipelineOutput(images=image)

kolors/pipelines/pipeline_stable_diffusion_xl_chatglm_256_ipadapter.py

@@ -1,948 +0,0 @@
-# Copyright 2023 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-import sys
-import os
-sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
-from kolors.models.modeling_chatglm import ChatGLMModel
-from kolors.models.tokenization_chatglm import ChatGLMTokenizer
-import inspect
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
-import torch
-from transformers import (
-    CLIPImageProcessor,
-    CLIPTextModel,
-    CLIPTextModelWithProjection,
-    CLIPTokenizer,
-    CLIPVisionModelWithProjection,
-)
-from transformers import XLMRobertaModel, ChineseCLIPTextModel
-
-from diffusers.image_processor import VaeImageProcessor,PipelineImageInput
-from diffusers.loaders import (
-    FromSingleFileMixin, 
-    IPAdapterMixin,
-    LoraLoaderMixin,
-    TextualInversionLoaderMixin
-)
-from diffusers.models import AutoencoderKL, UNet2DConditionModel,ImageProjection
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
-    XFormersAttnProcessor,
-)
-from diffusers.schedulers import KarrasDiffusionSchedulers
-from diffusers.utils import (
-    is_accelerate_available,
-    is_accelerate_version,
-    logging,
-    replace_example_docstring,
-)
-try:
-    from diffusers.utils import randn_tensor
-except:
-    from diffusers.utils.torch_utils import randn_tensor
-from diffusers.pipelines.pipeline_utils import DiffusionPipeline
-from diffusers.pipelines.stable_diffusion_xl import StableDiffusionXLPipelineOutput
-
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-EXAMPLE_DOC_STRING = """
-    Examples:
-        ```py
-        >>> import torch
-        >>> from diffusers import StableDiffusionXLPipeline
-
-        >>> pipe = StableDiffusionXLPipeline.from_pretrained(
-        ...     "stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16
-        ... )
-        >>> pipe = pipe.to("cuda")
-
-        >>> prompt = "a photo of an astronaut riding a horse on mars"
-        >>> image = pipe(prompt).images[0]
-        ```
-"""
-
-
-# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.rescale_noise_cfg
-def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
-    """
-    Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and
-    Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf). See Section 3.4
-    """
-    std_text = noise_pred_text.std(dim=list(range(1, noise_pred_text.ndim)), keepdim=True)
-    std_cfg = noise_cfg.std(dim=list(range(1, noise_cfg.ndim)), keepdim=True)
-    # rescale the results from guidance (fixes overexposure)
-    noise_pred_rescaled = noise_cfg * (std_text / std_cfg)
-    # mix with the original results from guidance by factor guidance_rescale to avoid "plain looking" images
-    noise_cfg = guidance_rescale * noise_pred_rescaled + (1 - guidance_rescale) * noise_cfg
-    return noise_cfg
-
-
-class StableDiffusionXLPipeline(DiffusionPipeline,  FromSingleFileMixin, LoraLoaderMixin, IPAdapterMixin,):
-    r"""
-    Pipeline for text-to-image generation using Stable Diffusion XL.
-
-    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
-    library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
-
-    In addition the pipeline inherits the following loading methods:
-        - *Textual-Inversion*: [`loaders.TextualInversionLoaderMixin.load_textual_inversion`]
-        - *LoRA*: [`loaders.LoraLoaderMixin.load_lora_weights`]
-        - *Ckpt*: [`loaders.FromSingleFileMixin.from_single_file`]
-
-    as well as the following saving methods:
-        - *LoRA*: [`loaders.LoraLoaderMixin.save_lora_weights`]
-
-    Args:
-        vae ([`AutoencoderKL`]):
-            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
-        text_encoder ([`CLIPTextModel`]):
-            Frozen text-encoder. Stable Diffusion XL uses the text portion of
-            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel), specifically
-            the [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) variant.
-
-        tokenizer (`CLIPTokenizer`):
-            Tokenizer of class
-            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
-
-        unet ([`UNet2DConditionModel`]): Conditional U-Net architecture to denoise the encoded image latents.
-        scheduler ([`SchedulerMixin`]):
-            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
-            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
-    """
-
-    def __init__(
-        self,
-        vae: AutoencoderKL,
-        text_encoder: ChatGLMModel,
-        tokenizer: ChatGLMTokenizer,
-        unet: UNet2DConditionModel,
-        scheduler: KarrasDiffusionSchedulers,
-        image_encoder: CLIPVisionModelWithProjection = None,
-        feature_extractor: CLIPImageProcessor = None,
-        force_zeros_for_empty_prompt: bool = True,
-    ):
-        super().__init__()
-
-        self.register_modules(
-            vae=vae,
-            text_encoder=text_encoder,
-            tokenizer=tokenizer,
-            unet=unet,
-            scheduler=scheduler,
-            image_encoder=image_encoder,
-            feature_extractor=feature_extractor,
-        )
-        self.register_to_config(force_zeros_for_empty_prompt=force_zeros_for_empty_prompt)
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
-        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
-        self.default_sample_size = self.unet.config.sample_size
-
-        # self.watermark = StableDiffusionXLWatermarker()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_vae_slicing
-    def enable_vae_slicing(self):
-        r"""
-        Enable sliced VAE decoding.
-
-        When this option is enabled, the VAE will split the input tensor in slices to compute decoding in several
-        steps. This is useful to save some memory and allow larger batch sizes.
-        """
-        self.vae.enable_slicing()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_vae_slicing
-    def disable_vae_slicing(self):
-        r"""
-        Disable sliced VAE decoding. If `enable_vae_slicing` was previously invoked, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_slicing()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_vae_tiling
-    def enable_vae_tiling(self):
-        r"""
-        Enable tiled VAE decoding.
-
-        When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and encoding in
-        several steps. This is useful to save a large amount of memory and to allow the processing of larger images.
-        """
-        self.vae.enable_tiling()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_vae_tiling
-    def disable_vae_tiling(self):
-        r"""
-        Disable tiled VAE decoding. If `enable_vae_tiling` was previously invoked, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_tiling()
-
-    def enable_sequential_cpu_offload(self, gpu_id=0):
-        r"""
-        Offloads all models to CPU using accelerate, significantly reducing memory usage. When called, unet,
-        text_encoder, vae and safety checker have their state dicts saved to CPU and then are moved to a
-        `torch.device('meta') and loaded to GPU only when their specific submodule has its `forward` method called.
-        Note that offloading happens on a submodule basis. Memory savings are higher than with
-        `enable_model_cpu_offload`, but performance is lower.
-        """
-        if is_accelerate_available() and is_accelerate_version(">=", "0.14.0"):
-            from accelerate import cpu_offload
-        else:
-            raise ImportError("`enable_sequential_cpu_offload` requires `accelerate v0.14.0` or higher")
-
-        device = torch.device(f"cuda:{gpu_id}")
-
-        if self.device.type != "cpu":
-            self.to("cpu", silence_dtype_warnings=True)
-            torch.cuda.empty_cache()  # otherwise we don't see the memory savings (but they probably exist)
-
-        for cpu_offloaded_model in [self.unet, self.text_encoder, self.vae]:
-            cpu_offload(cpu_offloaded_model, device)
-
-    def enable_model_cpu_offload(self, gpu_id=0):
-        r"""
-        Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared
-        to `enable_sequential_cpu_offload`, this method moves one whole model at a time to the GPU when its `forward`
-        method is called, and the model remains in GPU until the next model runs. Memory savings are lower than with
-        `enable_sequential_cpu_offload`, but performance is much better due to the iterative execution of the `unet`.
-        """
-        if is_accelerate_available() and is_accelerate_version(">=", "0.17.0.dev0"):
-            from accelerate import cpu_offload_with_hook
-        else:
-            raise ImportError("`enable_model_cpu_offload` requires `accelerate v0.17.0` or higher.")
-
-        device = torch.device(f"cuda:{gpu_id}")
-
-        if self.device.type != "cpu":
-            self.to("cpu", silence_dtype_warnings=True)
-            torch.cuda.empty_cache()  # otherwise we don't see the memory savings (but they probably exist)
-
-        model_sequence = (
-            [self.text_encoder, self.image_encoder]
-        )
-        model_sequence.extend([self.unet, self.vae])
-
-        hook = None
-        for cpu_offloaded_model in model_sequence:
-            _, hook = cpu_offload_with_hook(cpu_offloaded_model, device, prev_module_hook=hook)
-
-        # We'll offload the last model manually.
-        self.final_offload_hook = hook
-
-    @property
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline._execution_device
-    def _execution_device(self):
-        r"""
-        Returns the device on which the pipeline's models will be executed. After calling
-        `pipeline.enable_sequential_cpu_offload()` the execution device can only be inferred from Accelerate's module
-        hooks.
-        """
-        if not hasattr(self.unet, "_hf_hook"):
-            return self.device
-        for module in self.unet.modules():
-            if (
-                hasattr(module, "_hf_hook")
-                and hasattr(module._hf_hook, "execution_device")
-                and module._hf_hook.execution_device is not None
-            ):
-                return torch.device(module._hf_hook.execution_device)
-        return self.device
-
-    def encode_prompt(
-        self,
-        prompt,
-        device: Optional[torch.device] = None,
-        num_images_per_prompt: int = 1,
-        do_classifier_free_guidance: bool = True,
-        negative_prompt=None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        lora_scale: Optional[float] = None,
-    ):
-        r"""
-        Encodes the prompt into text encoder hidden states.
-
-        Args:
-             prompt (`str` or `List[str]`, *optional*):
-                prompt to be encoded
-            device: (`torch.device`):
-                torch device
-            num_images_per_prompt (`int`):
-                number of images that should be generated per prompt
-            do_classifier_free_guidance (`bool`):
-                whether to use classifier free guidance or not
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
-                If not provided, pooled text embeddings will be generated from `prompt` input argument.
-            negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
-                input argument.
-            lora_scale (`float`, *optional*):
-                A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
-        """
-        # from IPython import embed; embed(); exit()
-        device = device or self._execution_device
-
-        # set lora scale so that monkey patched LoRA
-        # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
-            self._lora_scale = lora_scale
-
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        # Define tokenizers and text encoders
-        tokenizers = [self.tokenizer]
-        text_encoders = [self.text_encoder]
-
-        if prompt_embeds is None:
-            # textual inversion: procecss multi-vector tokens if necessary
-            prompt_embeds_list = []
-            for tokenizer, text_encoder in zip(tokenizers, text_encoders):
-                if isinstance(self, TextualInversionLoaderMixin):
-                    prompt = self.maybe_convert_prompt(prompt, tokenizer)
-
-                text_inputs = tokenizer(
-                    prompt,
-                    padding="max_length",
-                    max_length=256,
-                    truncation=True,
-                    return_tensors="pt",
-                ).to('cuda')
-                output = text_encoder(
-                        input_ids=text_inputs['input_ids'] ,
-                        attention_mask=text_inputs['attention_mask'],
-                        position_ids=text_inputs['position_ids'],
-                        output_hidden_states=True)
-                prompt_embeds = output.hidden_states[-2].permute(1, 0, 2).clone()
-                pooled_prompt_embeds = output.hidden_states[-1][-1, :, :].clone() # [batch_size, 4096]
-                bs_embed, seq_len, _ = prompt_embeds.shape
-                prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
-                prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)
-
-                prompt_embeds_list.append(prompt_embeds)
-
-            # prompt_embeds = torch.concat(prompt_embeds_list, dim=-1)
-            prompt_embeds = prompt_embeds_list[0]
-
-        # get unconditional embeddings for classifier free guidance
-        zero_out_negative_prompt = negative_prompt is None and self.config.force_zeros_for_empty_prompt
-        if do_classifier_free_guidance and negative_prompt_embeds is None and zero_out_negative_prompt:
-            negative_prompt_embeds = torch.zeros_like(prompt_embeds)
-            negative_pooled_prompt_embeds = torch.zeros_like(pooled_prompt_embeds)
-        elif do_classifier_free_guidance and negative_prompt_embeds is None:
-            # negative_prompt = negative_prompt or ""
-            uncond_tokens: List[str]
-            if negative_prompt is None:
-                uncond_tokens = [""] * batch_size
-            elif prompt is not None and type(prompt) is not type(negative_prompt):
-                raise TypeError(
-                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
-                    f" {type(prompt)}."
-                )
-            elif isinstance(negative_prompt, str):
-                uncond_tokens = [negative_prompt]
-            elif batch_size != len(negative_prompt):
-                raise ValueError(
-                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
-                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
-                    " the batch size of `prompt`."
-                )
-            else:
-                uncond_tokens = negative_prompt
-
-            negative_prompt_embeds_list = []
-            for tokenizer, text_encoder in zip(tokenizers, text_encoders):
-                # textual inversion: procecss multi-vector tokens if necessary
-                if isinstance(self, TextualInversionLoaderMixin):
-                    uncond_tokens = self.maybe_convert_prompt(uncond_tokens, tokenizer)
-
-                max_length = prompt_embeds.shape[1]
-                uncond_input = tokenizer(
-                    uncond_tokens,
-                    padding="max_length",
-                    max_length=max_length,
-                    truncation=True,
-                    return_tensors="pt",
-                ).to('cuda')
-                output = text_encoder(
-                        input_ids=uncond_input['input_ids'] ,
-                        attention_mask=uncond_input['attention_mask'],
-                        position_ids=uncond_input['position_ids'],
-                        output_hidden_states=True)
-                negative_prompt_embeds = output.hidden_states[-2].permute(1, 0, 2).clone()
-                negative_pooled_prompt_embeds = output.hidden_states[-1][-1, :, :].clone() # [batch_size, 4096]
-
-                if do_classifier_free_guidance:
-                    # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
-                    seq_len = negative_prompt_embeds.shape[1]
-
-                    negative_prompt_embeds = negative_prompt_embeds.to(dtype=text_encoder.dtype, device=device)
-
-                    negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
-                    negative_prompt_embeds = negative_prompt_embeds.view(
-                        batch_size * num_images_per_prompt, seq_len, -1
-                    )
-
-                    # For classifier free guidance, we need to do two forward passes.
-                    # Here we concatenate the unconditional and text embeddings into a single batch
-                    # to avoid doing two forward passes
-
-                negative_prompt_embeds_list.append(negative_prompt_embeds)
-
-            # negative_prompt_embeds = torch.concat(negative_prompt_embeds_list, dim=-1)
-            negative_prompt_embeds = negative_prompt_embeds_list[0]
-
-        bs_embed = pooled_prompt_embeds.shape[0]
-        pooled_prompt_embeds = pooled_prompt_embeds.repeat(1, num_images_per_prompt).view(
-            bs_embed * num_images_per_prompt, -1
-        )
-        if do_classifier_free_guidance:
-            negative_pooled_prompt_embeds = negative_pooled_prompt_embeds.repeat(1, num_images_per_prompt).view(
-                bs_embed * num_images_per_prompt, -1
-            )
-
-        return prompt_embeds, negative_prompt_embeds, pooled_prompt_embeds, negative_pooled_prompt_embeds
-
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
-    def encode_image(self, image, device, num_images_per_prompt, output_hidden_states=None):
-        dtype = next(self.image_encoder.parameters()).dtype
-
-        if not isinstance(image, torch.Tensor):
-            image = self.feature_extractor(image, return_tensors="pt").pixel_values
-
-        image = image.to(device=device, dtype=dtype)
-        if output_hidden_states:
-            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True).hidden_states[-2]
-            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
-            uncond_image_enc_hidden_states = self.image_encoder(
-                torch.zeros_like(image), output_hidden_states=True
-            ).hidden_states[-2]
-            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
-                num_images_per_prompt, dim=0
-            )
-            return image_enc_hidden_states, uncond_image_enc_hidden_states
-        else:
-            image_embeds = self.image_encoder(image).image_embeds
-            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
-            uncond_image_embeds = torch.zeros_like(image_embeds)
-
-            return image_embeds, uncond_image_embeds
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_ip_adapter_image_embeds
-    def prepare_ip_adapter_image_embeds(
-        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
-    ):
-        image_embeds = []
-        if do_classifier_free_guidance:
-            negative_image_embeds = []
-        if ip_adapter_image_embeds is None:
-            if not isinstance(ip_adapter_image, list):
-                ip_adapter_image = [ip_adapter_image]
-
-            if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
-                raise ValueError(
-                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP Adapters."
-                )
-
-            for single_ip_adapter_image, image_proj_layer in zip(
-                ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
-            ):
-                output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
-                single_image_embeds, single_negative_image_embeds = self.encode_image(
-                    single_ip_adapter_image, device, 1, output_hidden_state
-                )
-
-                image_embeds.append(single_image_embeds[None, :])
-                if do_classifier_free_guidance:
-                    negative_image_embeds.append(single_negative_image_embeds[None, :])
-        else:
-            for single_image_embeds in ip_adapter_image_embeds:
-                if do_classifier_free_guidance:
-                    single_negative_image_embeds, single_image_embeds = single_image_embeds.chunk(2)
-                    negative_image_embeds.append(single_negative_image_embeds)
-                image_embeds.append(single_image_embeds)
-
-        ip_adapter_image_embeds = []
-        for i, single_image_embeds in enumerate(image_embeds):
-            single_image_embeds = torch.cat([single_image_embeds] * num_images_per_prompt, dim=0)
-            if do_classifier_free_guidance:
-                single_negative_image_embeds = torch.cat([negative_image_embeds[i]] * num_images_per_prompt, dim=0)
-                single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds], dim=0)
-
-            single_image_embeds = single_image_embeds.to(device=device)
-            ip_adapter_image_embeds.append(single_image_embeds)
-
-        return ip_adapter_image_embeds
-
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
-    def prepare_extra_step_kwargs(self, generator, eta):
-        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
-        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
-        # and should be between [0, 1]
-
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        # check if the scheduler accepts generator
-        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        if accepts_generator:
-            extra_step_kwargs["generator"] = generator
-        return extra_step_kwargs
-
-    def check_inputs(
-        self,
-        prompt,
-        height,
-        width,
-        callback_steps,
-        negative_prompt=None,
-        prompt_embeds=None,
-        negative_prompt_embeds=None,
-        pooled_prompt_embeds=None,
-        negative_pooled_prompt_embeds=None,
-    ):
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
-
-        if (callback_steps is None) or (
-            callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0)
-        ):
-            raise ValueError(
-                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
-                f" {type(callback_steps)}."
-            )
-
-        if prompt is not None and prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
-                " only forward one of the two."
-            )
-        elif prompt is None and prompt_embeds is None:
-            raise ValueError(
-                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
-            )
-        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
-            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
-
-        if negative_prompt is not None and negative_prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
-                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
-            )
-
-        if prompt_embeds is not None and negative_prompt_embeds is not None:
-            if prompt_embeds.shape != negative_prompt_embeds.shape:
-                raise ValueError(
-                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
-                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
-                    f" {negative_prompt_embeds.shape}."
-                )
-
-        if prompt_embeds is not None and pooled_prompt_embeds is None:
-            raise ValueError(
-                "If `prompt_embeds` are provided, `pooled_prompt_embeds` also have to be passed. Make sure to generate `pooled_prompt_embeds` from the same text encoder that was used to generate `prompt_embeds`."
-            )
-
-        if negative_prompt_embeds is not None and negative_pooled_prompt_embeds is None:
-            raise ValueError(
-                "If `negative_prompt_embeds` are provided, `negative_pooled_prompt_embeds` also have to be passed. Make sure to generate `negative_pooled_prompt_embeds` from the same text encoder that was used to generate `negative_prompt_embeds`."
-            )
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
-    def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
-        if isinstance(generator, list) and len(generator) != batch_size:
-            raise ValueError(
-                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
-                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
-            )
-
-        if latents is None:
-            latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-        else:
-            latents = latents.to(device)
-
-        # scale the initial noise by the standard deviation required by the scheduler
-        latents = latents * self.scheduler.init_noise_sigma
-        return latents
-
-    def _get_add_time_ids(self, original_size, crops_coords_top_left, target_size, dtype):
-        add_time_ids = list(original_size + crops_coords_top_left + target_size)
-
-        passed_add_embed_dim = (
-            self.unet.config.addition_time_embed_dim * len(add_time_ids) + 4096
-        )
-        expected_add_embed_dim = self.unet.add_embedding.linear_1.in_features
-
-        if expected_add_embed_dim != passed_add_embed_dim:
-            raise ValueError(
-                f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. The model has an incorrect config. Please check `unet.config.time_embedding_type` and `text_encoder_2.config.projection_dim`."
-            )
-
-        add_time_ids = torch.tensor([add_time_ids], dtype=dtype)
-        return add_time_ids
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
-    def upcast_vae(self):
-        dtype = self.vae.dtype
-        self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
-
-    @torch.no_grad()
-    @replace_example_docstring(EXAMPLE_DOC_STRING)
-    def __call__(
-        self,
-        prompt: Union[str, List[str]] = None,
-        height: Optional[int] = None,
-        width: Optional[int] = None,
-        num_inference_steps: int = 50,
-        denoising_end: Optional[float] = None,
-        guidance_scale: float = 5.0,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        num_images_per_prompt: Optional[int] = 1,
-        eta: float = 0.0,
-        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-
-        ip_adapter_image: Optional[PipelineImageInput] = None,
-        ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
-
-        output_type: Optional[str] = "pil",
-        return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
-        callback_steps: int = 1,
-        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-        guidance_rescale: float = 0.0,
-        original_size: Optional[Tuple[int, int]] = None,
-        crops_coords_top_left: Tuple[int, int] = (0, 0),
-        target_size: Optional[Tuple[int, int]] = None,
-        use_dynamic_threshold: Optional[bool] = False,
-    ):
-        r"""
-        Function invoked when calling the pipeline for generation.
-
-        Args:
-            prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
-                instead.
-            height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The height in pixels of the generated image.
-            width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The width in pixels of the generated image.
-            num_inference_steps (`int`, *optional*, defaults to 50):
-                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
-                expense of slower inference.
-            denoising_end (`float`, *optional*):
-                When specified, determines the fraction (between 0.0 and 1.0) of the total denoising process to be
-                completed before it is intentionally prematurely terminated. For instance, if denoising_end is set to
-                0.7 and `num_inference_steps` is fixed at 50, the process will execute only 35 (i.e., 0.7 * 50)
-                Denoisers" multi-pipeline setup, as elaborated in [**Refining the Image
-                Output**](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl#refining-the-image-output)
-            guidance_scale (`float`, *optional*, defaults to 7.5):
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
-                less than `1`).
-            num_images_per_prompt (`int`, *optional*, defaults to 1):
-                The number of images to generate per prompt.
-            eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
-                [`schedulers.DDIMScheduler`], will be ignored for others.
-            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
-                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
-                to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
-                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
-                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
-                tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
-                If not provided, pooled text embeddings will be generated from `prompt` input argument.
-            negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
-            output_type (`str`, *optional*, defaults to `"pil"`):
-                The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionXLPipelineOutput`] instead of a
-            callback (`Callable`, *optional*):
-                A function that will be called every `callback_steps` steps during inference. The function will be
-            callback_steps (`int`, *optional*, defaults to 1):
-                The frequency at which the `callback` function will be called. If not specified, the callback will be
-                called at every step.
-            cross_attention_kwargs (`dict`, *optional*):
-                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
-                `self.processor` in
-                [diffusers.cross_attention](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/cross_attention.py).
-            guidance_rescale (`float`, *optional*, defaults to 0.7):
-                Guidance rescale factor proposed by [Common Diffusion Noise Schedules and Sample Steps are
-                Flawed](https://arxiv.org/pdf/2305.08891.pdf) `guidance_scale` is defined as `φ` in equation 16. of
-                [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf).
-                Guidance rescale factor should fix overexposure when using zero terminal SNR.
-            original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                TODO
-            crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
-                TODO
-            target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                TODO
-
-        Examples:
-
-        Returns:
-            [`~pipelines.stable_diffusion.StableDiffusionXLPipelineOutput`] or `tuple`:
-            [`~pipelines.stable_diffusion.StableDiffusionXLPipelineOutput`] if `return_dict` is True, otherwise a
-            `tuple. When returning a tuple, the first element is a list with the generated images, and the second
-            element is a list of `bool`s denoting whether the corresponding generated image likely represents
-            "not-safe-for-work" (nsfw) content, according to the `safety_checker`.
-        """
-        # 0. Default height and width to unet
-        height = height or self.default_sample_size * self.vae_scale_factor
-        width = width or self.default_sample_size * self.vae_scale_factor
-
-        original_size = original_size or (height, width)
-        target_size = target_size or (height, width)
-
-        # 1. Check inputs. Raise error if not correct
-        self.check_inputs(
-            prompt,
-            height,
-            width,
-            callback_steps,
-            negative_prompt,
-            prompt_embeds,
-            negative_prompt_embeds,
-            pooled_prompt_embeds,
-            negative_pooled_prompt_embeds,
-        )
-
-        # 2. Define call parameters
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        device = self._execution_device
-
-        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
-        # corresponds to doing no classifier free guidance.
-        do_classifier_free_guidance = guidance_scale > 1.0
-
-        # 3. Encode input prompt
-        text_encoder_lora_scale = (
-            cross_attention_kwargs.get("scale", None) if cross_attention_kwargs is not None else None
-        )
-        (
-            prompt_embeds,
-            negative_prompt_embeds,
-            pooled_prompt_embeds,
-            negative_pooled_prompt_embeds,
-        ) = self.encode_prompt(
-            prompt,
-            device,
-            num_images_per_prompt,
-            do_classifier_free_guidance,
-            negative_prompt,
-            prompt_embeds=prompt_embeds,
-            negative_prompt_embeds=negative_prompt_embeds,
-            pooled_prompt_embeds=pooled_prompt_embeds,
-            negative_pooled_prompt_embeds=negative_pooled_prompt_embeds,
-            lora_scale=text_encoder_lora_scale,
-        )
-
-        # 4. Prepare timesteps
-        self.scheduler.set_timesteps(num_inference_steps, device=device)
-
-        timesteps = self.scheduler.timesteps
-
-        # 5. Prepare latent variables
-        num_channels_latents = self.unet.config.in_channels
-        latents = self.prepare_latents(
-            batch_size * num_images_per_prompt,
-            num_channels_latents,
-            height,
-            width,
-            prompt_embeds.dtype,
-            device,
-            generator,
-            latents,
-        )
-
-        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
-        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
-
-        # 7. Prepare added time ids & embeddings
-        add_text_embeds = pooled_prompt_embeds
-        add_time_ids = self._get_add_time_ids(
-            original_size, crops_coords_top_left, target_size, dtype=prompt_embeds.dtype
-        )
-
-        if do_classifier_free_guidance:
-            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
-            add_text_embeds = torch.cat([negative_pooled_prompt_embeds, add_text_embeds], dim=0)
-            add_time_ids = torch.cat([add_time_ids, add_time_ids], dim=0)
-
-        prompt_embeds = prompt_embeds.to(device)
-        add_text_embeds = add_text_embeds.to(device)
-        add_time_ids = add_time_ids.to(device).repeat(batch_size * num_images_per_prompt, 1)
-
-        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
-            image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image,
-                ip_adapter_image_embeds,
-                device,
-                batch_size * num_images_per_prompt,
-                do_classifier_free_guidance,
-            )
-
-        # 8. Denoising loop
-        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
-
-        # 7.1 Apply denoising_end
-        if denoising_end is not None:
-            num_inference_steps = int(round(denoising_end * num_inference_steps))
-            timesteps = timesteps[: num_warmup_steps + self.scheduler.order * num_inference_steps]
-
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            for i, t in enumerate(timesteps):
-                # expand the latents if we are doing classifier free guidance
-                latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
-
-                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
-
-                # predict the noise residual
-                added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
-                
-                if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
-                    added_cond_kwargs["image_embeds"] = image_embeds
-                
-                # import pdb; pdb.set_trace()
-
-                noise_pred = self.unet(
-                    latent_model_input,
-                    t,
-                    encoder_hidden_states=prompt_embeds,
-                    cross_attention_kwargs=cross_attention_kwargs,
-                    added_cond_kwargs=added_cond_kwargs,
-                    return_dict=False,
-                )[0]
-
-                # perform guidance
-                if do_classifier_free_guidance:
-                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
-                    if use_dynamic_threshold:
-                        DynamicThresh = DynThresh(maxSteps=num_inference_steps, experiment_mode=0)
-                        noise_pred = DynamicThresh.dynthresh(noise_pred_text,
-                            noise_pred_uncond,
-                            guidance_scale,
-                            None)
-
-                if do_classifier_free_guidance and guidance_rescale > 0.0:
-                    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
-                    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=guidance_rescale)
-
-                # compute the previous noisy sample x_t -> x_t-1
-                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
-
-                # call the callback, if provided
-                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
-                    progress_bar.update()
-                    if callback is not None and i % callback_steps == 0:
-                        callback(i, t, latents)
-
-        # make sureo the VAE is in float32 mode, as it overflows in float16
-        # torch.cuda.empty_cache()
-        if self.vae.dtype == torch.float16 and self.vae.config.force_upcast:
-            self.upcast_vae()
-            latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)
-
-
-        if not output_type == "latent":
-            latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)
-            image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
-        else:
-            image = latents
-            return StableDiffusionXLPipelineOutput(images=image)
-
-        # image = self.watermark.apply_watermark(image)
-        image = self.image_processor.postprocess(image, output_type=output_type)
-
-        # Offload last model to CPU
-        if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None:
-            self.final_offload_hook.offload()
-
-        if not return_dict:
-            return (image,)
-
-        return StableDiffusionXLPipelineOutput(images=image)
-
-
-if __name__ == "__main__":
-    pass