[Text-to-Video] Clean up pipeline (#6213)

* make style

* make style

* make style

* make style

src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_zero.py

 import copy
+import inspect
 from dataclasses import dataclass
 from typing import Callable, List, Optional, Union
 
@@ -9,11 +10,18 @@ import torch.nn.functional as F
 from torch.nn.functional import grid_sample
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
-from diffusers.models import AutoencoderKL, UNet2DConditionModel
-from diffusers.pipelines.stable_diffusion import StableDiffusionPipeline, StableDiffusionSafetyChecker
-from diffusers.schedulers import KarrasDiffusionSchedulers
-from diffusers.utils import BaseOutput
-from diffusers.utils.torch_utils import randn_tensor
+from ...image_processor import VaeImageProcessor
+from ...loaders import LoraLoaderMixin, TextualInversionLoaderMixin
+from ...models import AutoencoderKL, UNet2DConditionModel
+from ...models.lora import adjust_lora_scale_text_encoder
+from ...schedulers import KarrasDiffusionSchedulers
+from ...utils import USE_PEFT_BACKEND, BaseOutput, logging, scale_lora_layers, unscale_lora_layers
+from ...utils.torch_utils import randn_tensor
+from ..pipeline_utils import DiffusionPipeline
+from ..stable_diffusion import StableDiffusionSafetyChecker
+
+
+logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
 
 def rearrange_0(tensor, f):
@@ -273,7 +281,7 @@ def create_motion_field_and_warp_latents(motion_field_strength_x, motion_field_s
     return warped_latents
 
 
-class TextToVideoZeroPipeline(StableDiffusionPipeline):
+class TextToVideoZeroPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLoaderMixin):
     r"""
     Pipeline for zero-shot text-to-video generation using Stable Diffusion.
 
@@ -311,8 +319,15 @@ class TextToVideoZeroPipeline(StableDiffusionPipeline):
         feature_extractor: CLIPImageProcessor,
         requires_safety_checker: bool = True,
     ):
-        super().__init__(
-            vae, text_encoder, tokenizer, unet, scheduler, safety_checker, feature_extractor, requires_safety_checker
+        super().__init__()
+        self.register_modules(
+            vae=vae,
+            text_encoder=text_encoder,
+            tokenizer=tokenizer,
+            unet=unet,
+            scheduler=scheduler,
+            safety_checker=safety_checker,
+            feature_extractor=feature_extractor,
         )
         processor = (
             CrossFrameAttnProcessor2_0(batch_size=2)
@@ -321,6 +336,18 @@ class TextToVideoZeroPipeline(StableDiffusionPipeline):
         )
         self.unet.set_attn_processor(processor)
 
+        if safety_checker is None and requires_safety_checker:
+            logger.warning(
+                f"You have disabled the safety checker for {self.__class__} by passing `safety_checker=None`. Ensure"
+                " that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered"
+                " results in services or applications open to the public. Both the diffusers team and Hugging Face"
+                " strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling"
+                " it only for use-cases that involve analyzing network behavior or auditing its results. For more"
+                " information, please have a look at https://github.com/huggingface/diffusers/pull/254 ."
+            )
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
+        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
+
     def forward_loop(self, x_t0, t0, t1, generator):
         """
         Perform DDPM forward process from time t0 to t1. This is the same as adding noise with corresponding variance.
@@ -420,6 +447,77 @@ class TextToVideoZeroPipeline(StableDiffusionPipeline):
                         callback(step_idx, t, latents)
         return latents.clone().detach()
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.check_inputs
+    def check_inputs(
+        self,
+        prompt,
+        height,
+        width,
+        callback_steps,
+        negative_prompt=None,
+        prompt_embeds=None,
+        negative_prompt_embeds=None,
+        callback_on_step_end_tensor_inputs=None,
+    ):
+        if height % 8 != 0 or width % 8 != 0:
+            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
+
+        if 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 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 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}."
+                )
+
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
+    def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
+        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        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."
+            )
+
+        if latents is None:
+            latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
+        else:
+            latents = latents.to(device)
+
+        # scale the initial noise by the standard deviation required by the scheduler
+        latents = latents * self.scheduler.init_noise_sigma
+        return latents
+
     @torch.no_grad()
     def __call__(
         self,
@@ -539,9 +637,10 @@ class TextToVideoZeroPipeline(StableDiffusionPipeline):
         do_classifier_free_guidance = guidance_scale > 1.0
 
         # Encode input prompt
-        prompt_embeds = self._encode_prompt(
+        prompt_embeds_tuple = self.encode_prompt(
             prompt, device, num_videos_per_prompt, do_classifier_free_guidance, negative_prompt
         )
+        prompt_embeds = torch.cat([prompt_embeds_tuple[1], prompt_embeds_tuple[0]])
 
         # Prepare timesteps
         self.scheduler.set_timesteps(num_inference_steps, device=device)
@@ -645,3 +744,226 @@ class TextToVideoZeroPipeline(StableDiffusionPipeline):
             return (image, has_nsfw_concept)
 
         return TextToVideoPipelineOutput(images=image, nsfw_content_detected=has_nsfw_concept)
+
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
+    def run_safety_checker(self, image, device, dtype):
+        if self.safety_checker is None:
+            has_nsfw_concept = None
+        else:
+            if torch.is_tensor(image):
+                feature_extractor_input = self.image_processor.postprocess(image, output_type="pil")
+            else:
+                feature_extractor_input = self.image_processor.numpy_to_pil(image)
+            safety_checker_input = self.feature_extractor(feature_extractor_input, return_tensors="pt").to(device)
+            image, has_nsfw_concept = self.safety_checker(
+                images=image, clip_input=safety_checker_input.pixel_values.to(dtype)
+            )
+        return image, has_nsfw_concept
+
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
+    def prepare_extra_step_kwargs(self, generator, eta):
+        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
+        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
+        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
+        # and should be between [0, 1]
+
+        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
+        extra_step_kwargs = {}
+        if accepts_eta:
+            extra_step_kwargs["eta"] = eta
+
+        # check if the scheduler accepts generator
+        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
+        if accepts_generator:
+            extra_step_kwargs["generator"] = generator
+        return extra_step_kwargs
+
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_prompt
+    def encode_prompt(
+        self,
+        prompt,
+        device,
+        num_images_per_prompt,
+        do_classifier_free_guidance,
+        negative_prompt=None,
+        prompt_embeds: Optional[torch.FloatTensor] = None,
+        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        lora_scale: Optional[float] = None,
+        clip_skip: Optional[int] = None,
+    ):
+        r"""
+        Encodes the prompt into text encoder hidden states.
+
+        Args:
+            prompt (`str` or `List[str]`, *optional*):
+                prompt to be encoded
+            device: (`torch.device`):
+                torch device
+            num_images_per_prompt (`int`):
+                number of images that should be generated per prompt
+            do_classifier_free_guidance (`bool`):
+                whether to use classifier free guidance or not
+            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`).
+            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.
+            lora_scale (`float`, *optional*):
+                A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
+            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.
+        """
+        # set lora scale so that monkey patched LoRA
+        # function of text encoder can correctly access it
+        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
+            self._lora_scale = lora_scale
+
+            # dynamically adjust the LoRA scale
+            if not USE_PEFT_BACKEND:
+                adjust_lora_scale_text_encoder(self.text_encoder, lora_scale)
+            else:
+                scale_lora_layers(self.text_encoder, lora_scale)
+
+        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]
+
+        if prompt_embeds is None:
+            # textual inversion: procecss multi-vector tokens if necessary
+            if isinstance(self, TextualInversionLoaderMixin):
+                prompt = self.maybe_convert_prompt(prompt, self.tokenizer)
+
+            text_inputs = self.tokenizer(
+                prompt,
+                padding="max_length",
+                max_length=self.tokenizer.model_max_length,
+                truncation=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[:, self.tokenizer.model_max_length - 1 : -1]
+                )
+                logger.warning(
+                    "The following part of your input was truncated because CLIP can only handle sequences up to"
+                    f" {self.tokenizer.model_max_length} tokens: {removed_text}"
+                )
+
+            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
+                attention_mask = text_inputs.attention_mask.to(device)
+            else:
+                attention_mask = None
+
+            if clip_skip is None:
+                prompt_embeds = self.text_encoder(text_input_ids.to(device), attention_mask=attention_mask)
+                prompt_embeds = prompt_embeds[0]
+            else:
+                prompt_embeds = self.text_encoder(
+                    text_input_ids.to(device), attention_mask=attention_mask, output_hidden_states=True
+                )
+                # Access the `hidden_states` first, that contains a tuple of
+                # all the hidden states from the encoder layers. Then index into
+                # the tuple to access the hidden states from the desired layer.
+                prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)]
+                # We also need to apply the final LayerNorm here to not mess with the
+                # representations. The `last_hidden_states` that we typically use for
+                # obtaining the final prompt representations passes through the LayerNorm
+                # layer.
+                prompt_embeds = self.text_encoder.text_model.final_layer_norm(prompt_embeds)
+
+        if self.text_encoder is not None:
+            prompt_embeds_dtype = self.text_encoder.dtype
+        elif self.unet is not None:
+            prompt_embeds_dtype = self.unet.dtype
+        else:
+            prompt_embeds_dtype = prompt_embeds.dtype
+
+        prompt_embeds = prompt_embeds.to(dtype=prompt_embeds_dtype, device=device)
+
+        bs_embed, seq_len, _ = prompt_embeds.shape
+        # duplicate text embeddings for each generation per prompt, using mps friendly method
+        prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
+        prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)
+
+        # get unconditional embeddings for classifier free guidance
+        if do_classifier_free_guidance and negative_prompt_embeds is None:
+            uncond_tokens: List[str]
+            if negative_prompt is None:
+                uncond_tokens = [""] * batch_size
+            elif 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 isinstance(negative_prompt, str):
+                uncond_tokens = [negative_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`."
+                )
+            else:
+                uncond_tokens = negative_prompt
+
+            # textual inversion: procecss multi-vector tokens if necessary
+            if isinstance(self, TextualInversionLoaderMixin):
+                uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer)
+
+            max_length = prompt_embeds.shape[1]
+            uncond_input = self.tokenizer(
+                uncond_tokens,
+                padding="max_length",
+                max_length=max_length,
+                truncation=True,
+                return_tensors="pt",
+            )
+
+            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
+                attention_mask = uncond_input.attention_mask.to(device)
+            else:
+                attention_mask = None
+
+            negative_prompt_embeds = self.text_encoder(
+                uncond_input.input_ids.to(device),
+                attention_mask=attention_mask,
+            )
+            negative_prompt_embeds = negative_prompt_embeds[0]
+
+        if do_classifier_free_guidance:
+            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
+            seq_len = negative_prompt_embeds.shape[1]
+
+            negative_prompt_embeds = negative_prompt_embeds.to(dtype=prompt_embeds_dtype, device=device)
+
+            negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
+            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
+
+        if isinstance(self, LoraLoaderMixin) and USE_PEFT_BACKEND:
+            # Retrieve the original scale by scaling back the LoRA layers
+            unscale_lora_layers(self.text_encoder, lora_scale)
+
+        return prompt_embeds, negative_prompt_embeds
+
+    def decode_latents(self, latents):
+        latents = 1 / self.vae.config.scaling_factor * latents
+        image = self.vae.decode(latents, return_dict=False)[0]
+        image = (image / 2 + 0.5).clamp(0, 1)
+        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
+        image = image.cpu().permute(0, 2, 3, 1).float().numpy()
+        return image

tests/pipelines/text_to_video_synthesis/test_text_to_video_zero_sdxl.py

@@ -383,7 +383,7 @@ class TextToVideoZeroSDXLPipelineFastTests(PipelineTesterMixin, unittest.TestCas
 class TextToVideoZeroSDXLPipelineSlowTests(unittest.TestCase):
     def test_full_model(self):
         model_id = "stabilityai/stable-diffusion-xl-base-1.0"
-        pipe = self.pipeline_class.from_pretrained(
+        pipe = TextToVideoZeroSDXLPipeline.from_pretrained(
             model_id, torch_dtype=torch.float16, variant="fp16", use_safetensors=True
         )
         pipe.enable_model_cpu_offload()