diffusers-version/tora/i2v_pipeline.py [158:343]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - r""" Pipeline for image-to-video generation using Tora. 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.) Args: vae ([`AutoencoderKL`]): Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations. text_encoder ([`T5EncoderModel`]): Frozen text-encoder. Tora uses [T5](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5EncoderModel); specifically the [t5-v1_1-xxl](https://huggingface.co/PixArt-alpha/PixArt-alpha/tree/main/t5-v1_1-xxl) variant. tokenizer (`T5Tokenizer`): Tokenizer of class [T5Tokenizer](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5Tokenizer). transformer ([`ToraTransformer3DModel`]): A text and flow conditioned `ToraTransformer3DModel` to denoise the encoded video latents. scheduler ([`SchedulerMixin`]): A scheduler to be used in combination with `transformer` to denoise the encoded video latents. """ _optional_components = [] model_cpu_offload_seq = "text_encoder->transformer->vae" _callback_tensor_inputs = [ "latents", "prompt_embeds", "negative_prompt_embeds", ] def __init__( self, tokenizer: T5Tokenizer, text_encoder: T5EncoderModel, vae: AutoencoderKLCogVideoX, transformer: ToraTransformer3DModel, scheduler: Union[CogVideoXDDIMScheduler, CogVideoXDPMScheduler], ): super().__init__() self.register_modules( tokenizer=tokenizer, text_encoder=text_encoder, vae=vae, transformer=transformer, scheduler=scheduler, ) self.vae_scale_factor_spatial = ( 2 ** (len(self.vae.config.block_out_channels) - 1) if hasattr(self, "vae") and self.vae is not None else 8 ) self.vae_scale_factor_temporal = ( self.vae.config.temporal_compression_ratio if hasattr(self, "vae") and self.vae is not None else 4 ) self.vae_scaling_factor_image = ( self.vae.config.scaling_factor if hasattr(self, "vae") and self.vae is not None else 0.7 ) self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor_spatial) # Copied from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline._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 batch_size = len(prompt) text_inputs = self.tokenizer( prompt, padding="max_length", max_length=max_sequence_length, truncation=True, add_special_tokens=True, return_tensors="pt", ) text_input_ids = text_inputs.input_ids untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="pt").input_ids if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal(text_input_ids, untruncated_ids): removed_text = self.tokenizer.batch_decode(untruncated_ids[:, max_sequence_length - 1 : -1]) logger.warning( "The following part of your input was truncated because `max_sequence_length` is set to " f" {max_sequence_length} tokens: {removed_text}" ) prompt_embeds = self.text_encoder(text_input_ids.to(device))[0] prompt_embeds = prompt_embeds.to(dtype=dtype, device=device) # 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.cogvideo.pipeline_cogvideox.CogVideoXPipeline.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 prepare_latents( self, - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diffusers-version/tora/t2v_pipeline.py [145:329]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - r""" Pipeline for text-to-video generation using Tora. 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.) Args: vae ([`AutoencoderKL`]): Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations. text_encoder ([`T5EncoderModel`]): Frozen text-encoder. Tora uses [T5](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5EncoderModel); specifically the [t5-v1_1-xxl](https://huggingface.co/PixArt-alpha/PixArt-alpha/tree/main/t5-v1_1-xxl) variant. tokenizer (`T5Tokenizer`): Tokenizer of class [T5Tokenizer](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5Tokenizer). transformer ([`ToraTransformer3DModel`]): A text and flow conditioned `ToraTransformer3DModel` to denoise the encoded video latents. scheduler ([`SchedulerMixin`]): A scheduler to be used in combination with `transformer` to denoise the encoded video latents. """ _optional_components = [] model_cpu_offload_seq = "text_encoder->transformer->vae" _callback_tensor_inputs = [ "latents", "prompt_embeds", "negative_prompt_embeds", ] def __init__( self, tokenizer: T5Tokenizer, text_encoder: T5EncoderModel, vae: AutoencoderKLCogVideoX, transformer: ToraTransformer3DModel, scheduler: Union[CogVideoXDDIMScheduler, CogVideoXDPMScheduler], ): super().__init__() self.register_modules( tokenizer=tokenizer, text_encoder=text_encoder, vae=vae, transformer=transformer, scheduler=scheduler, ) self.vae_scale_factor_spatial = ( 2 ** (len(self.vae.config.block_out_channels) - 1) if hasattr(self, "vae") and self.vae is not None else 8 ) self.vae_scale_factor_temporal = ( self.vae.config.temporal_compression_ratio if hasattr(self, "vae") and self.vae is not None else 4 ) self.vae_scaling_factor_image = ( self.vae.config.scaling_factor if hasattr(self, "vae") and self.vae is not None else 0.7 ) self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor_spatial) # Copied from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline._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 batch_size = len(prompt) text_inputs = self.tokenizer( prompt, padding="max_length", max_length=max_sequence_length, truncation=True, add_special_tokens=True, return_tensors="pt", ) text_input_ids = text_inputs.input_ids untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="pt").input_ids if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal(text_input_ids, untruncated_ids): removed_text = self.tokenizer.batch_decode(untruncated_ids[:, max_sequence_length - 1 : -1]) logger.warning( "The following part of your input was truncated because `max_sequence_length` is set to " f" {max_sequence_length} tokens: {removed_text}" ) prompt_embeds = self.text_encoder(text_input_ids.to(device))[0] prompt_embeds = prompt_embeds.to(dtype=dtype, device=device) # 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 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 prepare_latents( self, - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -