|
from typing import Any, Callable, Dict, List, Optional, Union |
|
from diffusers.pipelines.controlnet.pipeline_controlnet import StableDiffusionControlNetPipeline, EXAMPLE_DOC_STRING |
|
from diffusers.pipelines.controlnet.multicontrolnet import MultiControlNetModel |
|
from diffusers.utils import logging, replace_example_docstring |
|
from diffusers.image_processor import PipelineImageInput |
|
from diffusers.utils.torch_utils import is_compiled_module, is_torch_version |
|
from diffusers.pipelines.stable_diffusion.pipeline_output import StableDiffusionPipelineOutput |
|
|
|
import torch.nn.functional as F |
|
import torch |
|
from .controlnet_SPADE import ControlNetModel |
|
|
|
logger = logging.get_logger(__name__) |
|
|
|
class StableDiffusionControlNetPipeline_SPADE(StableDiffusionControlNetPipeline): |
|
def check_inputs( |
|
self, |
|
prompt, |
|
image, |
|
callback_steps, |
|
negative_prompt=None, |
|
prompt_embeds=None, |
|
negative_prompt_embeds=None, |
|
controlnet_conditioning_scale=1.0, |
|
control_guidance_start=0.0, |
|
control_guidance_end=1.0, |
|
): |
|
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 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." |
|
) |
|
|
|
|
|
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`") |
|
|
|
|
|
|
|
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 |
|
|
|
|
|
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.") |
|
|
|
@torch.no_grad() |
|
@replace_example_docstring(EXAMPLE_DOC_STRING) |
|
def __call__( |
|
self, |
|
prompt: Union[str, List[str]] = None, |
|
image: PipelineImageInput = None, |
|
height: Optional[int] = None, |
|
width: Optional[int] = None, |
|
num_inference_steps: int = 50, |
|
guidance_scale: float = 7.5, |
|
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, |
|
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, |
|
controlnet_conditioning_scale: Union[float, List[float]] = 1.0, |
|
guess_mode: bool = False, |
|
control_guidance_start: Union[float, List[float]] = 0.0, |
|
control_guidance_end: Union[float, List[float]] = 1.0, |
|
clip_skip: Optional[int] = None, |
|
): |
|
r""" |
|
The call function to the pipeline for generation. |
|
|
|
Args: |
|
prompt (`str` or `List[str]`, *optional*): |
|
The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`. |
|
image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,: |
|
`List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`): |
|
The ControlNet input condition to provide guidance to the `unet` for generation. If the type is |
|
specified as `torch.FloatTensor`, 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 accordingly. 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 `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. |
|
guidance_scale (`float`, *optional*, defaults to 7.5): |
|
A higher guidance scale value encourages the model to generate images closely linked to the text |
|
`prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`. |
|
negative_prompt (`str` or `List[str]`, *optional*): |
|
The prompt or prompts to guide what to not include in image generation. If not defined, you need to |
|
pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 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) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies |
|
to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers. |
|
generator (`torch.Generator` or `List[torch.Generator]`, *optional*): |
|
A [`torch.Generator`](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 is 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 (prompt weighting). If not |
|
provided, text embeddings are generated from the `prompt` input argument. |
|
negative_prompt_embeds (`torch.FloatTensor`, *optional*): |
|
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If |
|
not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument. |
|
output_type (`str`, *optional*, defaults to `"pil"`): |
|
The output format of the generated image. Choose between `PIL.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. |
|
callback (`Callable`, *optional*): |
|
A function that calls every `callback_steps` steps during inference. The function is called with the |
|
following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`. |
|
callback_steps (`int`, *optional*, defaults to 1): |
|
The frequency at which the `callback` function is called. If not specified, the callback is called at |
|
every step. |
|
cross_attention_kwargs (`dict`, *optional*): |
|
A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in |
|
[`self.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. |
|
guess_mode (`bool`, *optional*, defaults to `False`): |
|
The ControlNet encoder tries to recognize the content of the input image even if you remove all |
|
prompts. A `guidance_scale` value between 3.0 and 5.0 is recommended. |
|
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. |
|
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. |
|
|
|
Examples: |
|
|
|
Returns: |
|
[`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`: |
|
If `return_dict` is `True`, [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] is returned, |
|
otherwise a `tuple` is returned where the first element is a list with the generated images and the |
|
second element is a list of `bool`s indicating whether the corresponding generated image contains |
|
"not-safe-for-work" (nsfw) content. |
|
""" |
|
controlnet = self.controlnet._orig_mod if is_compiled_module(self.controlnet) else self.controlnet |
|
|
|
|
|
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 |
|
] |
|
|
|
|
|
self.check_inputs( |
|
prompt, |
|
image, |
|
callback_steps, |
|
negative_prompt, |
|
prompt_embeds, |
|
negative_prompt_embeds, |
|
controlnet_conditioning_scale, |
|
control_guidance_start, |
|
control_guidance_end, |
|
) |
|
|
|
|
|
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 |
|
|
|
|
|
|
|
do_classifier_free_guidance = guidance_scale > 1.0 |
|
|
|
if isinstance(controlnet, MultiControlNetModel) and isinstance(controlnet_conditioning_scale, float): |
|
controlnet_conditioning_scale = [controlnet_conditioning_scale] * len(controlnet.nets) |
|
|
|
global_pool_conditions = ( |
|
controlnet.config.global_pool_conditions |
|
if isinstance(controlnet, ControlNetModel) |
|
else controlnet.nets[0].config.global_pool_conditions |
|
) |
|
guess_mode = guess_mode or global_pool_conditions |
|
|
|
|
|
text_encoder_lora_scale = ( |
|
cross_attention_kwargs.get("scale", None) if cross_attention_kwargs is not None else None |
|
) |
|
prompt_embeds, negative_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, |
|
lora_scale=text_encoder_lora_scale, |
|
clip_skip=clip_skip, |
|
) |
|
|
|
|
|
|
|
if do_classifier_free_guidance: |
|
prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds]) |
|
|
|
|
|
if isinstance(controlnet, ControlNetModel): |
|
image = self.prepare_image( |
|
image=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=do_classifier_free_guidance, |
|
guess_mode=guess_mode, |
|
) |
|
height, width = image.shape[-2:] |
|
elif isinstance(controlnet, MultiControlNetModel): |
|
images = [] |
|
|
|
for image_ in image: |
|
image_ = self.prepare_image( |
|
image=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=do_classifier_free_guidance, |
|
guess_mode=guess_mode, |
|
) |
|
|
|
images.append(image_) |
|
|
|
image = images |
|
height, width = image[0].shape[-2:] |
|
else: |
|
assert False |
|
|
|
|
|
self.scheduler.set_timesteps(num_inference_steps, device=device) |
|
timesteps = self.scheduler.timesteps |
|
|
|
|
|
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, |
|
) |
|
|
|
|
|
extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta) |
|
|
|
|
|
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) |
|
|
|
|
|
num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order |
|
is_unet_compiled = is_compiled_module(self.unet) |
|
is_controlnet_compiled = is_compiled_module(self.controlnet) |
|
is_torch_higher_equal_2_1 = is_torch_version(">=", "2.1") |
|
with self.progress_bar(total=num_inference_steps) as progress_bar: |
|
for i, t in enumerate(timesteps): |
|
|
|
|
|
if (is_unet_compiled and is_controlnet_compiled) and is_torch_higher_equal_2_1: |
|
torch._inductor.cudagraph_mark_step_begin() |
|
|
|
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) |
|
|
|
|
|
if guess_mode and do_classifier_free_guidance: |
|
|
|
control_model_input = latents |
|
control_model_input = self.scheduler.scale_model_input(control_model_input, t) |
|
controlnet_prompt_embeds = prompt_embeds.chunk(2)[1] |
|
else: |
|
control_model_input = latent_model_input |
|
controlnet_prompt_embeds = prompt_embeds |
|
|
|
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=image, |
|
conditioning_scale=cond_scale, |
|
guess_mode=guess_mode, |
|
return_dict=False, |
|
) |
|
|
|
if guess_mode and do_classifier_free_guidance: |
|
|
|
|
|
|
|
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]) |
|
|
|
|
|
noise_pred = self.unet( |
|
latent_model_input, |
|
t, |
|
encoder_hidden_states=prompt_embeds, |
|
cross_attention_kwargs=cross_attention_kwargs, |
|
down_block_additional_residuals=down_block_res_samples, |
|
mid_block_additional_residual=mid_block_res_sample, |
|
return_dict=False, |
|
)[0] |
|
|
|
|
|
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) |
|
|
|
|
|
latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0] |
|
|
|
|
|
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 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": |
|
image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0] |
|
image, has_nsfw_concept = self.run_safety_checker(image, device, prompt_embeds.dtype) |
|
else: |
|
image = latents |
|
has_nsfw_concept = None |
|
|
|
if has_nsfw_concept is None: |
|
do_denormalize = [True] * image.shape[0] |
|
else: |
|
do_denormalize = [not has_nsfw for has_nsfw in has_nsfw_concept] |
|
|
|
image = self.image_processor.postprocess(image, output_type=output_type, do_denormalize=do_denormalize) |
|
|
|
|
|
self.maybe_free_model_hooks() |
|
|
|
if not return_dict: |
|
return (image, has_nsfw_concept) |
|
|
|
return StableDiffusionPipelineOutput(images=image, nsfw_content_detected=has_nsfw_concept) |