Spaces:
Runtime error
Runtime error
| from typing import Any, Callable, Dict, List, Optional, Union | |
| import torch | |
| from diffusers.utils import replace_example_docstring | |
| from transformers import CLIPTokenizer | |
| from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion import StableDiffusionPipeline, EXAMPLE_DOC_STRING | |
| from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput | |
| from NestedScheduler import NestedScheduler | |
| class NestedStableDiffusionPipeline(StableDiffusionPipeline): | |
| r""" | |
| Pipeline for text-to-image generation using Nested Stable Diffusion. | |
| 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.FromCkptMixin.from_ckpt`] | |
| 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 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`]. | |
| safety_checker ([`StableDiffusionSafetyChecker`]): | |
| Classification module that estimates whether generated images could be considered offensive or harmful. | |
| Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details. | |
| feature_extractor ([`CLIPImageProcessor`]): | |
| Model that extracts features from generated images to be used as inputs for the `safety_checker`. | |
| """ | |
| def __call__( | |
| self, | |
| prompt: Union[str, List[str]] = None, | |
| height: Optional[int] = None, | |
| width: Optional[int] = None, | |
| num_inference_steps: int = 5, | |
| num_inner_steps: int = 20, | |
| guidance_scale: float = 7.5, | |
| negative_prompt: Optional[Union[str, List[str]]] = None, | |
| num_images_per_prompt: Optional[int] = 1, | |
| eta: float = 0.0, | |
| inner_eta: float = 0.85, | |
| 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, | |
| coroutine_mode=True): | |
| 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 5): | |
| The number of outer denoising steps. | |
| num_inner_steps (`int`, *optional*, defaults to 20): | |
| The number of inner denoising steps. | |
| 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 outer diffusion process | |
| inner_eta (`float`, *optional*, defaults to 0.85): | |
| Corresponds to parameter eta (η) in the inner diffusion process | |
| 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. | |
| 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. | |
| callback (`Callable`, *optional*): | |
| A function that will be called every `callback_steps` steps during inference. The function will be | |
| 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 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). | |
| Examples: | |
| Returns: | |
| [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`: | |
| [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] 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.unet.config.sample_size * self.vae_scale_factor | |
| width = width or self.unet.config.sample_size * self.vae_scale_factor | |
| # 1. Check inputs. Raise error if not correct | |
| self.check_inputs( | |
| prompt, height, width, callback_steps, negative_prompt, prompt_embeds, negative_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 | |
| 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, | |
| ) | |
| # 4. Prepare timesteps | |
| self.scheduler.set_timesteps(num_inference_steps + 1, device=device) | |
| timesteps = self.scheduler.timesteps[:-1] | |
| # 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. | |
| extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta) | |
| inner_extra_step_kwargs = self.prepare_extra_step_kwargs(generator, inner_eta) | |
| # 7. Denoising loop | |
| outer_latents = latents.clone() | |
| num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order | |
| # running the outer diffusion procees | |
| anytime_latent = outer_latents.clone() | |
| with self.progress_bar(total=num_inference_steps) as progress_bar: | |
| for i, t in enumerate(timesteps): | |
| # creating the inner diffusion process | |
| self.inner_scheduler = NestedScheduler(beta_start=0.00085, beta_end=0.012, | |
| beta_schedule="scaled_linear", clip_sample=False, | |
| set_alpha_to_one=False, thresholding=False) | |
| self.inner_scheduler.set_timesteps(num_inner_steps, max_timestep=t.item(), device=device) | |
| inner_timesteps = self.inner_scheduler.timesteps | |
| latents = outer_latents.clone() | |
| # running the inner diffusion procees | |
| for j, t_tag in enumerate(inner_timesteps): | |
| yield (i, j, self.decode_latents(anytime_latent)) | |
| # 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.inner_scheduler.scale_model_input(latent_model_input, t_tag) | |
| # predict the noise residual | |
| noise_pred = self.unet(latent_model_input, t_tag, encoder_hidden_states=prompt_embeds).sample | |
| # 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) | |
| latents = self.inner_scheduler.step(noise_pred, t_tag, latents, **inner_extra_step_kwargs).prev_sample | |
| anytime_latent = latents.clone() | |
| # compute the previous noisy sample x_t -> x_t-1 | |
| outer_latents = self.scheduler.step(latents, t, outer_latents, **extra_step_kwargs).prev_sample | |
| # 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) | |
| yield (i+1, j+1, self.decode_latents(outer_latents)) |