diff --git a/src/diffusers/__init__.py b/src/diffusers/__init__.py index d96acc3818d8..167d39c6e8df 100644 --- a/src/diffusers/__init__.py +++ b/src/diffusers/__init__.py @@ -495,6 +495,7 @@ "LTXImageToVideoPipeline", "LTXLatentUpsamplePipeline", "LTXPipeline", + "LucyEditPipeline", "Lumina2Pipeline", "Lumina2Text2ImgPipeline", "LuminaPipeline", @@ -1149,6 +1150,7 @@ LTXImageToVideoPipeline, LTXLatentUpsamplePipeline, LTXPipeline, + LucyEditPipeline, Lumina2Pipeline, Lumina2Text2ImgPipeline, LuminaPipeline, diff --git a/src/diffusers/pipelines/__init__.py b/src/diffusers/pipelines/__init__.py index 8ed07a72e3fd..17f3fc909e4d 100644 --- a/src/diffusers/pipelines/__init__.py +++ b/src/diffusers/pipelines/__init__.py @@ -285,6 +285,7 @@ ] _import_structure["lumina"] = ["LuminaPipeline", "LuminaText2ImgPipeline"] _import_structure["lumina2"] = ["Lumina2Pipeline", "Lumina2Text2ImgPipeline"] + _import_structure["lucy"] = ["LucyEditPipeline"] _import_structure["marigold"].extend( [ "MarigoldDepthPipeline", @@ -682,6 +683,7 @@ LEditsPPPipelineStableDiffusionXL, ) from .ltx import LTXConditionPipeline, LTXImageToVideoPipeline, LTXLatentUpsamplePipeline, LTXPipeline + from .lucy import LucyEditPipeline from .lumina import LuminaPipeline, LuminaText2ImgPipeline from .lumina2 import Lumina2Pipeline, Lumina2Text2ImgPipeline from .marigold import ( diff --git a/src/diffusers/pipelines/lucy/__init__.py b/src/diffusers/pipelines/lucy/__init__.py new file mode 100644 index 000000000000..580e1f37f30a --- /dev/null +++ b/src/diffusers/pipelines/lucy/__init__.py @@ -0,0 +1,47 @@ +from typing import TYPE_CHECKING + +from ...utils import ( + DIFFUSERS_SLOW_IMPORT, + OptionalDependencyNotAvailable, + _LazyModule, + get_objects_from_module, + is_torch_available, + is_transformers_available, +) + + +_dummy_objects = {} +_import_structure = {} + + +try: + if not (is_transformers_available() and is_torch_available()): + raise OptionalDependencyNotAvailable() +except OptionalDependencyNotAvailable: + from ...utils import dummy_torch_and_transformers_objects # noqa F403 + + _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects)) +else: + _import_structure["pipeline_lucy_edit"] = ["LucyEditPipeline"] +if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT: + try: + if not (is_transformers_available() and is_torch_available()): + raise OptionalDependencyNotAvailable() + + except OptionalDependencyNotAvailable: + from ...utils.dummy_torch_and_transformers_objects import * + else: + from .pipeline_lucy_edit import LucyEditPipeline + +else: + import sys + + sys.modules[__name__] = _LazyModule( + __name__, + globals()["__file__"], + _import_structure, + module_spec=__spec__, + ) + + for name, value in _dummy_objects.items(): + setattr(sys.modules[__name__], name, value) diff --git a/src/diffusers/pipelines/lucy/pipeline_lucy_edit.py b/src/diffusers/pipelines/lucy/pipeline_lucy_edit.py new file mode 100644 index 000000000000..2a4dcbf1ec16 --- /dev/null +++ b/src/diffusers/pipelines/lucy/pipeline_lucy_edit.py @@ -0,0 +1,736 @@ +# Copyright 2025 The Wan Team and The HuggingFace Team. All rights reserved. +# Copyright 2025 The Decart AI 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. +# +# Modifications by Decart AI Team: +# - Based on pipeline_wan.py, but with supports recieving a condition video appended to the channel dimension. + +import html +from typing import Any, Callable, Dict, List, Optional, Tuple, Union + +import regex as re +import torch +from PIL import Image +from transformers import AutoTokenizer, UMT5EncoderModel + +from ...callbacks import MultiPipelineCallbacks, PipelineCallback +from ...loaders import WanLoraLoaderMixin +from ...models import AutoencoderKLWan, WanTransformer3DModel +from ...schedulers import FlowMatchEulerDiscreteScheduler +from ...utils import is_ftfy_available, is_torch_xla_available, logging, replace_example_docstring +from ...utils.torch_utils import randn_tensor +from ...video_processor import VideoProcessor +from ..pipeline_utils import DiffusionPipeline +from .pipeline_output import LucyPipelineOutput + + +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 + +if is_ftfy_available(): + import ftfy + + +EXAMPLE_DOC_STRING = """ + Examples: + ```python +>>> from typing import List + +>>> import torch +>>> from PIL import Image + +>>> from diffusers import AutoencoderKLWan, WanTransformer3DModel +>>> from diffusers.pipelines.lucy.pipeline_lucy_edit import LucyEditPipeline +>>> from diffusers.utils import export_to_video, load_video + +>>> # Arguments +>>> url = "https://d2drjpuinn46lb.cloudfront.net/painter_original_edit.mp4" +>>> prompt = "Change the apron and blouse to a classic clown costume: satin polka-dot jumpsuit in bright primary colors, ruffled white collar, oversized pom-pom buttons, white gloves, oversized red shoes, red foam nose; soft window light from left, eye-level medium shot, natural folds and fabric highlights." +>>> negative_prompt = "" +>>> num_frames = 81 +>>> height = 480 +>>> width = 832 + + +>>> # Load video +>>> def convert_video(video: List[Image.Image]) -> List[Image.Image]: + ... video = load_video(url)[:num_frames] + ... video = [video[i].resize((width, height)) for i in range(num_frames)] + ... return video + + +>>> video = load_video(url, convert_method=convert_video) + +>>> # Load model +>>> model_id = "decart-ai/Lucy-Edit-Dev" +>>> vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32) +>>> pipe = LucyEditPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16) +>>> pipe.to("cuda") + +>>> # Generate video +>>> output = pipe( + ... prompt=prompt, + ... video=video, + ... negative_prompt=negative_prompt, + ... height=480, + ... width=832, + ... num_frames=81, + ... guidance_scale=5.0, + ... ).frames[0] + +>>> # Export video +>>> export_to_video(output, "output.mp4", fps=24) + ``` +""" + + +def basic_clean(text): + text = ftfy.fix_text(text) + text = html.unescape(html.unescape(text)) + return text.strip() + + +def whitespace_clean(text): + text = re.sub(r"\s+", " ", text) + text = text.strip() + return text + + +def prompt_clean(text): + text = whitespace_clean(basic_clean(text)) + return text + + +# 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 LucyEditPipeline(DiffusionPipeline, WanLoraLoaderMixin): + r""" + Pipeline for video-to-video generation using Lucy Edit. + + This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods + implemented for all pipelines (downloading, saving, running on a particular device, etc.). + + Args: + tokenizer ([`T5Tokenizer`]): + Tokenizer from [T5](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5Tokenizer), + specifically the [google/umt5-xxl](https://huggingface.co/google/umt5-xxl) variant. + text_encoder ([`T5EncoderModel`]): + [T5](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5EncoderModel), specifically + the [google/umt5-xxl](https://huggingface.co/google/umt5-xxl) variant. + transformer ([`WanTransformer3DModel`]): + Conditional Transformer to denoise the input latents. + scheduler ([`UniPCMultistepScheduler`]): + A scheduler to be used in combination with `transformer` to denoise the encoded image latents. + vae ([`AutoencoderKLWan`]): + Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations. + transformer_2 ([`WanTransformer3DModel`], *optional*): + Conditional Transformer to denoise the input latents during the low-noise stage. If provided, enables + two-stage denoising where `transformer` handles high-noise stages and `transformer_2` handles low-noise + stages. If not provided, only `transformer` is used. + boundary_ratio (`float`, *optional*, defaults to `None`): + Ratio of total timesteps to use as the boundary for switching between transformers in two-stage denoising. + The actual boundary timestep is calculated as `boundary_ratio * num_train_timesteps`. When provided, + `transformer` handles timesteps>= boundary_timestep and `transformer_2` handles timesteps < + boundary_timestep. If `None`, only `transformer` is used for the entire denoising process. + """ + + model_cpu_offload_seq = "text_encoder->transformer->transformer_2->vae" + _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"] + _optional_components = ["transformer", "transformer_2"] + + def __init__( + self, + tokenizer: AutoTokenizer, + text_encoder: UMT5EncoderModel, + vae: AutoencoderKLWan, + scheduler: FlowMatchEulerDiscreteScheduler, + transformer: Optional[WanTransformer3DModel] = None, + transformer_2: Optional[WanTransformer3DModel] = None, + boundary_ratio: Optional[float] = None, + expand_timesteps: bool = False, # Wan2.2 ti2v + ): + super().__init__() + + self.register_modules( + vae=vae, + text_encoder=text_encoder, + tokenizer=tokenizer, + transformer=transformer, + scheduler=scheduler, + transformer_2=transformer_2, + ) + self.register_to_config(boundary_ratio=boundary_ratio) + self.register_to_config(expand_timesteps=expand_timesteps) + self.vae_scale_factor_temporal = self.vae.config.scale_factor_temporal if getattr(self, "vae", None) else 4 + self.vae_scale_factor_spatial = self.vae.config.scale_factor_spatial if getattr(self, "vae", None) else 8 + self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor_spatial) + + # Copied from diffusers.pipelines.wan.pipeline_wan.WanPipeline._get_t5_prompt_embeds + def _get_t5_prompt_embeds( + self, + prompt: Union[str, List[str]] = None, + num_videos_per_prompt: int = 1, + max_sequence_length: int = 226, + device: Optional[torch.device] = None, + dtype: Optional[torch.dtype] = None, + ): + device = device or self._execution_device + dtype = dtype or self.text_encoder.dtype + + prompt = [prompt] if isinstance(prompt, str) else prompt + prompt = [prompt_clean(u) for u in prompt] + batch_size = len(prompt) + + text_inputs = self.tokenizer( + prompt, + padding="max_length", + max_length=max_sequence_length, + truncation=True, + add_special_tokens=True, + return_attention_mask=True, + return_tensors="pt", + ) + text_input_ids, mask = text_inputs.input_ids, text_inputs.attention_mask + seq_lens = mask.gt(0).sum(dim=1).long() + + prompt_embeds = self.text_encoder(text_input_ids.to(device), mask.to(device)).last_hidden_state + prompt_embeds = prompt_embeds.to(dtype=dtype, device=device) + prompt_embeds = [u[:v] for u, v in zip(prompt_embeds, seq_lens)] + prompt_embeds = torch.stack( + [torch.cat([u, u.new_zeros(max_sequence_length - u.size(0), u.size(1))]) for u in prompt_embeds], dim=0 + ) + + # duplicate text embeddings for each generation per prompt, using mps friendly method + _, seq_len, _ = prompt_embeds.shape + prompt_embeds = prompt_embeds.repeat(1, num_videos_per_prompt, 1) + prompt_embeds = prompt_embeds.view(batch_size * num_videos_per_prompt, seq_len, -1) + + return prompt_embeds + + # Copied from diffusers.pipelines.wan.pipeline_wan.WanPipeline.encode_prompt + def encode_prompt( + self, + prompt: Union[str, List[str]], + negative_prompt: Optional[Union[str, List[str]]] = None, + do_classifier_free_guidance: bool = True, + num_videos_per_prompt: int = 1, + prompt_embeds: Optional[torch.Tensor] = None, + negative_prompt_embeds: Optional[torch.Tensor] = None, + max_sequence_length: int = 226, + device: Optional[torch.device] = None, + dtype: Optional[torch.dtype] = None, + ): + r""" + Encodes the prompt into text encoder hidden states. + + Args: + prompt (`str` or `List[str]`, *optional*): + prompt to be encoded + 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`). + do_classifier_free_guidance (`bool`, *optional*, defaults to `True`): + Whether to use classifier free guidance or not. + num_videos_per_prompt (`int`, *optional*, defaults to 1): + Number of videos that should be generated per prompt. torch device to place the resulting embeddings on + 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. + device: (`torch.device`, *optional*): + torch device + dtype: (`torch.dtype`, *optional*): + torch dtype + """ + device = device or self._execution_device + + prompt = [prompt] if isinstance(prompt, str) else prompt + if prompt is not None: + batch_size = len(prompt) + else: + batch_size = prompt_embeds.shape[0] + + if prompt_embeds is None: + prompt_embeds = self._get_t5_prompt_embeds( + prompt=prompt, + num_videos_per_prompt=num_videos_per_prompt, + max_sequence_length=max_sequence_length, + device=device, + dtype=dtype, + ) + + if do_classifier_free_guidance and negative_prompt_embeds is None: + negative_prompt = negative_prompt or "" + negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt + + if 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 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`." + ) + + negative_prompt_embeds = self._get_t5_prompt_embeds( + prompt=negative_prompt, + num_videos_per_prompt=num_videos_per_prompt, + max_sequence_length=max_sequence_length, + device=device, + dtype=dtype, + ) + + return prompt_embeds, negative_prompt_embeds + + def check_inputs( + self, + video, + prompt, + negative_prompt, + height, + width, + prompt_embeds=None, + negative_prompt_embeds=None, + callback_on_step_end_tensor_inputs=None, + guidance_scale_2=None, + ): + if height % 16 != 0 or width % 16 != 0: + raise ValueError(f"`height` and `width` have to be divisible by 16 but are {height} and {width}.") + + 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 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`: {negative_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 negative_prompt is not None and ( + not isinstance(negative_prompt, str) and not isinstance(negative_prompt, list) + ): + raise ValueError(f"`negative_prompt` has to be of type `str` or `list` but is {type(negative_prompt)}") + + if self.config.boundary_ratio is None and guidance_scale_2 is not None: + raise ValueError("`guidance_scale_2` is only supported when the pipeline's `boundary_ratio` is not None.") + + if video is None: + raise ValueError("`video` is required, received None.") + + def prepare_latents( + self, + video: Optional[torch.Tensor] = None, + batch_size: int = 1, + num_channels_latents: int = 16, + height: int = 480, + width: int = 832, + dtype: Optional[torch.dtype] = None, + device: Optional[torch.device] = None, + generator: Optional[torch.Generator] = None, + latents: Optional[torch.Tensor] = None, + ) -> Tuple[torch.Tensor, torch.Tensor]: + 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." + ) + + num_latent_frames = ( + (video.size(2) - 1) // self.vae_scale_factor_temporal + 1 if latents is None else latents.size(1) + ) + shape = ( + batch_size, + num_channels_latents, + num_latent_frames, + height // self.vae_scale_factor_spatial, + width // self.vae_scale_factor_spatial, + ) + # Prepare noise latents + if latents is None: + latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype) + else: + latents = latents.to(device) + + # Prepare condition latents + condition_latents = [ + retrieve_latents(self.vae.encode(vid.unsqueeze(0)), sample_mode="argmax") for vid in video + ] + + condition_latents = torch.cat(condition_latents, dim=0).to(dtype) + + latents_mean = ( + torch.tensor(self.vae.config.latents_mean).view(1, self.vae.config.z_dim, 1, 1, 1).to(device, dtype) + ) + latents_std = 1.0 / torch.tensor(self.vae.config.latents_std).view(1, self.vae.config.z_dim, 1, 1, 1).to( + device, dtype + ) + + condition_latents = (condition_latents - latents_mean) * latents_std + + # Check shapes + assert latents.shape == condition_latents.shape, ( + f"Latents shape {latents.shape} does not match expected shape {condition_latents.shape}. Please check the input." + ) + + return latents, condition_latents + + @property + def guidance_scale(self): + return self._guidance_scale + + @property + def do_classifier_free_guidance(self): + return self._guidance_scale> 1.0 + + @property + def num_timesteps(self): + return self._num_timesteps + + @property + def current_timestep(self): + return self._current_timestep + + @property + def interrupt(self): + return self._interrupt + + @property + def attention_kwargs(self): + return self._attention_kwargs + + @torch.no_grad() + @replace_example_docstring(EXAMPLE_DOC_STRING) + def __call__( + self, + video: List[Image.Image], + prompt: Union[str, List[str]] = None, + negative_prompt: Union[str, List[str]] = None, + height: int = 480, + width: int = 832, + num_frames: int = 81, + num_inference_steps: int = 50, + guidance_scale: float = 5.0, + guidance_scale_2: Optional[float] = None, + num_videos_per_prompt: Optional[int] = 1, + 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, + output_type: Optional[str] = "np", + return_dict: bool = True, + attention_kwargs: Optional[Dict[str, Any]] = None, + callback_on_step_end: Optional[ + Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks] + ] = None, + callback_on_step_end_tensor_inputs: List[str] = ["latents"], + max_sequence_length: int = 512, + ): + r""" + The call function to the pipeline for generation. + + Args: + video (`List[Image.Image]`): + The video to use as the condition for the video generation. + prompt (`str` or `List[str]`, *optional*): + The prompt or prompts to guide the image generation. If not defined, pass `prompt_embeds` instead. + negative_prompt (`str` or `List[str]`, *optional*): + The prompt or prompts to avoid during image generation. If not defined, pass `negative_prompt_embeds` + instead. Ignored when not using guidance (`guidance_scale` < `1`). + height (`int`, defaults to `480`): + The height in pixels of the generated image. + width (`int`, defaults to `832`): + The width in pixels of the generated image. + num_frames (`int`, defaults to `81`): + The number of frames in the generated video. + num_inference_steps (`int`, 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`, defaults to `5.0`): + Guidance scale as defined in [Classifier-Free Diffusion + Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2. + of [Imagen Paper](https://huggingface.co/papers/2205.11487). 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. + guidance_scale_2 (`float`, *optional*, defaults to `None`): + Guidance scale for the low-noise stage transformer (`transformer_2`). If `None` and the pipeline's + `boundary_ratio` is not None, uses the same value as `guidance_scale`. Only used when `transformer_2` + and the pipeline's `boundary_ratio` are not None. + num_videos_per_prompt (`int`, *optional*, defaults to 1): + The number of images to generate per prompt. + 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.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 is 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 (prompt weighting). If not + provided, text embeddings are generated from the `prompt` input argument. + output_type (`str`, *optional*, defaults to `"np"`): + 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 [`LucyPipelineOutput`] instead of a plain tuple. + 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). + 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. + max_sequence_length (`int`, defaults to `512`): + The maximum sequence length of the text encoder. If the prompt is longer than this, it will be + truncated. If the prompt is shorter, it will be padded to this length. + + Examples: + + Returns: + [`~LucyPipelineOutput`] or `tuple`: + If `return_dict` is `True`, [`LucyPipelineOutput`] 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. + """ + + if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)): + callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs + + # 1. Check inputs. Raise error if not correct + self.check_inputs( + video, + prompt, + negative_prompt, + height, + width, + prompt_embeds, + negative_prompt_embeds, + callback_on_step_end_tensor_inputs, + guidance_scale_2, + ) + + if num_frames % self.vae_scale_factor_temporal != 1: + logger.warning( + f"`num_frames - 1` has to be divisible by {self.vae_scale_factor_temporal}. Rounding to the nearest number." + ) + num_frames = num_frames // self.vae_scale_factor_temporal * self.vae_scale_factor_temporal + 1 + num_frames = max(num_frames, 1) + + if self.config.boundary_ratio is not None and guidance_scale_2 is None: + guidance_scale_2 = guidance_scale + + self._guidance_scale = guidance_scale + self._guidance_scale_2 = guidance_scale_2 + self._attention_kwargs = attention_kwargs + self._current_timestep = None + self._interrupt = False + + device = self._execution_device + + # 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] + + # 3. Encode input prompt + prompt_embeds, negative_prompt_embeds = self.encode_prompt( + prompt=prompt, + negative_prompt=negative_prompt, + do_classifier_free_guidance=self.do_classifier_free_guidance, + num_videos_per_prompt=num_videos_per_prompt, + prompt_embeds=prompt_embeds, + negative_prompt_embeds=negative_prompt_embeds, + max_sequence_length=max_sequence_length, + device=device, + ) + + transformer_dtype = self.transformer.dtype if self.transformer is not None else self.transformer_2.dtype + prompt_embeds = prompt_embeds.to(transformer_dtype) + if negative_prompt_embeds is not None: + negative_prompt_embeds = negative_prompt_embeds.to(transformer_dtype) + + # 4. Prepare timesteps + self.scheduler.set_timesteps(num_inference_steps, device=device) + timesteps = self.scheduler.timesteps + + # 5. Prepare latent variables + num_channels_latents = ( + self.transformer.config.out_channels + if self.transformer is not None + else self.transformer_2.config.out_channels + ) + video = self.video_processor.preprocess_video(video, height=height, width=width).to( + device, dtype=torch.float32 + ) + latents, condition_latents = self.prepare_latents( + video, + batch_size * num_videos_per_prompt, + num_channels_latents, + height, + width, + torch.float32, + device, + generator, + latents, + ) + + mask = torch.ones(latents.shape, dtype=torch.float32, device=device) + + # 6. Denoising loop + num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order + self._num_timesteps = len(timesteps) + + if self.config.boundary_ratio is not None: + boundary_timestep = self.config.boundary_ratio * self.scheduler.config.num_train_timesteps + else: + boundary_timestep = None + + with self.progress_bar(total=num_inference_steps) as progress_bar: + for i, t in enumerate(timesteps): + if self.interrupt: + continue + + self._current_timestep = t + + if boundary_timestep is None or t>= boundary_timestep: + # wan2.1 or high-noise stage in wan2.2 + current_model = self.transformer + current_guidance_scale = guidance_scale + else: + # low-noise stage in wan2.2 + current_model = self.transformer_2 + current_guidance_scale = guidance_scale_2 + + # latent_model_input = latents.to(transformer_dtype) + latent_model_input = torch.cat([latents, condition_latents], dim=1).to(transformer_dtype) + # latent_model_input = torch.cat([latents, latents], dim=1).to(transformer_dtype) + if self.config.expand_timesteps: + # seq_len: num_latent_frames * latent_height//2 * latent_width//2 + temp_ts = (mask[0][0][:, ::2, ::2] * t).flatten() + # batch_size, seq_len + timestep = temp_ts.unsqueeze(0).expand(latents.shape[0], -1) + else: + timestep = t.expand(latents.shape[0]) + + with current_model.cache_context("cond"): + noise_pred = current_model( + hidden_states=latent_model_input, + timestep=timestep, + encoder_hidden_states=prompt_embeds, + attention_kwargs=attention_kwargs, + return_dict=False, + )[0] + + if self.do_classifier_free_guidance: + with current_model.cache_context("uncond"): + noise_uncond = current_model( + hidden_states=latent_model_input, + timestep=timestep, + encoder_hidden_states=negative_prompt_embeds, + attention_kwargs=attention_kwargs, + return_dict=False, + )[0] + noise_pred = noise_uncond + current_guidance_scale * (noise_pred - noise_uncond) + + # compute the previous noisy sample x_t -> x_t-1 + latents = self.scheduler.step(noise_pred, t, latents, return_dict=False)[0] + + 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) + + # 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 XLA_AVAILABLE: + xm.mark_step() + + self._current_timestep = None + + if not output_type == "latent": + latents = latents.to(self.vae.dtype) + latents_mean = ( + torch.tensor(self.vae.config.latents_mean) + .view(1, self.vae.config.z_dim, 1, 1, 1) + .to(latents.device, latents.dtype) + ) + latents_std = 1.0 / torch.tensor(self.vae.config.latents_std).view(1, self.vae.config.z_dim, 1, 1, 1).to( + latents.device, latents.dtype + ) + latents = latents / latents_std + latents_mean + video = self.vae.decode(latents, return_dict=False)[0] + video = self.video_processor.postprocess_video(video, output_type=output_type) + else: + video = latents + + # Offload all models + self.maybe_free_model_hooks() + + if not return_dict: + return (video,) + + return LucyPipelineOutput(frames=video) diff --git a/src/diffusers/pipelines/lucy/pipeline_output.py b/src/diffusers/pipelines/lucy/pipeline_output.py new file mode 100644 index 000000000000..cf9ea91fd106 --- /dev/null +++ b/src/diffusers/pipelines/lucy/pipeline_output.py @@ -0,0 +1,20 @@ +from dataclasses import dataclass + +import torch + +from diffusers.utils import BaseOutput + + +@dataclass +class LucyPipelineOutput(BaseOutput): + r""" + Output class for Lucy pipelines. + + Args: + frames (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]): + List of video outputs - It can be a nested list of length `batch_size,` with each sub-list containing + denoised PIL image sequences of length `num_frames.` It can also be a NumPy array or Torch tensor of shape + `(batch_size, num_frames, channels, height, width)`. + """ + + frames: torch.Tensor diff --git a/src/diffusers/utils/dummy_torch_and_transformers_objects.py b/src/diffusers/utils/dummy_torch_and_transformers_objects.py index 00792fa55a05..e29be174f02e 100644 --- a/src/diffusers/utils/dummy_torch_and_transformers_objects.py +++ b/src/diffusers/utils/dummy_torch_and_transformers_objects.py @@ -1592,6 +1592,21 @@ def from_pretrained(cls, *args, **kwargs): requires_backends(cls, ["torch", "transformers"]) +class LucyEditPipeline(metaclass=DummyObject): + _backends = ["torch", "transformers"] + + def __init__(self, *args, **kwargs): + requires_backends(self, ["torch", "transformers"]) + + @classmethod + def from_config(cls, *args, **kwargs): + requires_backends(cls, ["torch", "transformers"]) + + @classmethod + def from_pretrained(cls, *args, **kwargs): + requires_backends(cls, ["torch", "transformers"]) + + class Lumina2Pipeline(metaclass=DummyObject): _backends = ["torch", "transformers"]

AltStyle によって変換されたページ (->オリジナル) /