from typing import Any, Callable, Dict, List, Optional, Union import torch from diffusers.callbacks import MultiPipelineCallbacks, PipelineCallback from diffusers.utils import is_torch_xla_available, logging, replace_example_docstring from diffusers.pipelines.wan.pipeline_output import WanPipelineOutput from diffusers.pipelines.wan.pipeline_wan import WanPipeline from src.attention_wan_nag import NAGWanAttnProcessor2_0 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 class NAGWanPipeline(WanPipeline): @property def do_normalized_attention_guidance(self): return self._nag_scale > 1 def _set_nag_attn_processor(self, nag_scale, nag_tau, nag_alpha): attn_procs = {} for name, origin_attn_proc in self.transformer.attn_processors.items(): if "attn2" in name: attn_procs[name] = NAGWanAttnProcessor2_0(nag_scale=nag_scale, nag_tau=nag_tau, nag_alpha=nag_alpha) else: attn_procs[name] = origin_attn_proc self.transformer.set_attn_processor(attn_procs) @torch.no_grad() def __call__( self, 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, 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, nag_scale: float = 1.0, nag_tau: float = 2.5, nag_alpha: float = 0.25, nag_negative_prompt: str = None, nag_negative_prompt_embeds: Optional[torch.Tensor] = None, ): r""" The call function to 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`, 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://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. 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 `"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 [`WanPipelineOutput`] 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. autocast_dtype (`torch.dtype`, *optional*, defaults to `torch.bfloat16`): The dtype to use for the torch.amp.autocast. Examples: Returns: [`~WanPipelineOutput`] or `tuple`: If `return_dict` is `True`, [`WanPipelineOutput`] 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( prompt, negative_prompt, height, width, prompt_embeds, negative_prompt_embeds, callback_on_step_end_tensor_inputs, ) self._guidance_scale = guidance_scale self._attention_kwargs = attention_kwargs self._current_timestep = None self._interrupt = False self._nag_scale = nag_scale 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, ) if self.do_normalized_attention_guidance: if nag_negative_prompt_embeds is None: if nag_negative_prompt is None: if self.do_classifier_free_guidance: nag_negative_prompt_embeds = negative_prompt_embeds else: nag_negative_prompt = negative_prompt or "" if nag_negative_prompt is not None: nag_negative_prompt_embeds = self.encode_prompt( prompt=nag_negative_prompt, do_classifier_free_guidance=False, num_videos_per_prompt=num_videos_per_prompt, max_sequence_length=max_sequence_length, device=device, )[0] if self.do_normalized_attention_guidance: prompt_embeds = torch.cat([prompt_embeds, nag_negative_prompt_embeds], dim=0) transformer_dtype = self.transformer.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.in_channels latents = self.prepare_latents( batch_size * num_videos_per_prompt, num_channels_latents, height, width, num_frames, torch.float32, device, generator, latents, ) # 6. Denoising loop num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order self._num_timesteps = len(timesteps) if self.do_normalized_attention_guidance: origin_attn_procs = self.transformer.attn_processors self._set_nag_attn_processor(nag_scale, nag_tau, nag_alpha) 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 latent_model_input = latents.to(transformer_dtype) timestep = t.expand(latents.shape[0]) noise_pred = self.transformer( 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: noise_uncond = self.transformer( 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 + 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 if self.do_normalized_attention_guidance: self.transformer.set_attn_processor(origin_attn_procs) # Offload all models self.maybe_free_model_hooks() if not return_dict: return (video,) return WanPipelineOutput(frames=video)