diffusers 0.23.0__py3-none-any.whl → 0.24.0__py3-none-any.whl

diffusers/pipelines/alt_diffusion/pipeline_alt_diffusion_img2img.py

@@ -19,11 +19,11 @@ import numpy as np
 import PIL.Image
 import torch
 from packaging import version
-from transformers import CLIPImageProcessor, XLMRobertaTokenizer
+from transformers import CLIPImageProcessor, CLIPVisionModelWithProjection, XLMRobertaTokenizer
 
 from ...configuration_utils import FrozenDict
 from ...image_processor import PipelineImageInput, VaeImageProcessor
-from ...loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInversionLoaderMixin
+from ...loaders import FromSingleFileMixin, IPAdapterMixin, LoraLoaderMixin, TextualInversionLoaderMixin
 from ...models import AutoencoderKL, UNet2DConditionModel
 from ...models.lora import adjust_lora_scale_text_encoder
 from ...schedulers import KarrasDiffusionSchedulers
@@ -76,9 +76,13 @@ EXAMPLE_DOC_STRING = """
 
 
 # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.retrieve_latents
-def retrieve_latents(encoder_output, generator):
-    if hasattr(encoder_output, "latent_dist"):
+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:
@@ -109,9 +113,54 @@ def preprocess(image):
     return image
 
 
+# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.retrieve_timesteps
+def retrieve_timesteps(
+    scheduler,
+    num_inference_steps: Optional[int] = None,
+    device: Optional[Union[str, torch.device]] = None,
+    timesteps: Optional[List[int]] = None,
+    **kwargs,
+):
+    """
+    Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles
+    custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`.
+
+    Args:
+        scheduler (`SchedulerMixin`):
+            The scheduler to get timesteps from.
+        num_inference_steps (`int`):
+            The number of diffusion steps used when generating samples with a pre-trained model. If used,
+            `timesteps` must be `None`.
+        device (`str` or `torch.device`, *optional*):
+            The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
+        timesteps (`List[int]`, *optional*):
+                Custom timesteps used to support arbitrary spacing between timesteps. If `None`, then the default
+                timestep spacing strategy of the scheduler is used. If `timesteps` is passed, `num_inference_steps`
+                must be `None`.
+
+    Returns:
+        `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
+        second element is the number of inference steps.
+    """
+    if timesteps is not None:
+        accepts_timesteps = "timesteps" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
+        if not accepts_timesteps:
+            raise ValueError(
+                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
+                f" timestep schedules. Please check whether you are using the correct scheduler."
+            )
+        scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs)
+        timesteps = scheduler.timesteps
+        num_inference_steps = len(timesteps)
+    else:
+        scheduler.set_timesteps(num_inference_steps, device=device, **kwargs)
+        timesteps = scheduler.timesteps
+    return timesteps, num_inference_steps
+
+
 # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.StableDiffusionImg2ImgPipeline with Stable->Alt, CLIPTextModel->RobertaSeriesModelWithTransformation, CLIPTokenizer->XLMRobertaTokenizer, AltDiffusionSafetyChecker->StableDiffusionSafetyChecker
 class AltDiffusionImg2ImgPipeline(
-    DiffusionPipeline, TextualInversionLoaderMixin, LoraLoaderMixin, FromSingleFileMixin
+    DiffusionPipeline, TextualInversionLoaderMixin, IPAdapterMixin, LoraLoaderMixin, FromSingleFileMixin
 ):
     r"""
     Pipeline for text-guided image-to-image generation using Alt Diffusion.
@@ -124,6 +173,7 @@ class AltDiffusionImg2ImgPipeline(
         - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
         - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
+        - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
 
     Args:
         vae ([`AutoencoderKL`]):
@@ -146,7 +196,7 @@ class AltDiffusionImg2ImgPipeline(
     """
 
     model_cpu_offload_seq = "text_encoder->unet->vae"
-    _optional_components = ["safety_checker", "feature_extractor"]
+    _optional_components = ["safety_checker", "feature_extractor", "image_encoder"]
     _exclude_from_cpu_offload = ["safety_checker"]
     _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]
 
@@ -159,6 +209,7 @@ class AltDiffusionImg2ImgPipeline(
         scheduler: KarrasDiffusionSchedulers,
         safety_checker: StableDiffusionSafetyChecker,
         feature_extractor: CLIPImageProcessor,
+        image_encoder: CLIPVisionModelWithProjection = None,
         requires_safety_checker: bool = True,
     ):
         super().__init__()
@@ -235,6 +286,7 @@ class AltDiffusionImg2ImgPipeline(
             scheduler=scheduler,
             safety_checker=safety_checker,
             feature_extractor=feature_extractor,
+            image_encoder=image_encoder,
         )
         self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
@@ -252,10 +304,7 @@ class AltDiffusionImg2ImgPipeline(
         lora_scale: Optional[float] = None,
         **kwargs,
     ):
-        deprecation_message = (
-            "`_encode_prompt()` is deprecated and it will be removed in a future version. Use `encode_prompt()`"
-            " instead. Also, be aware that the output format changed from a concatenated tensor to a tuple."
-        )
+        deprecation_message = "`_encode_prompt()` is deprecated and it will be removed in a future version. Use `encode_prompt()` instead. Also, be aware that the output format changed from a concatenated tensor to a tuple."
         deprecate("_encode_prompt()", "1.0.0", deprecation_message, standard_warn=False)
 
         prompt_embeds_tuple = self.encode_prompt(
@@ -456,6 +505,19 @@ class AltDiffusionImg2ImgPipeline(
 
         return prompt_embeds, negative_prompt_embeds
 
+    def encode_image(self, image, device, num_images_per_prompt):
+        dtype = next(self.image_encoder.parameters()).dtype
+
+        if not isinstance(image, torch.Tensor):
+            image = self.feature_extractor(image, return_tensors="pt").pixel_values
+
+        image = image.to(device=device, dtype=dtype)
+        image_embeds = self.image_encoder(image).image_embeds
+        image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
+
+        uncond_image_embeds = torch.zeros_like(image_embeds)
+        return image_embeds, uncond_image_embeds
+
     def run_safety_checker(self, image, device, dtype):
         if self.safety_checker is None:
             has_nsfw_concept = None
@@ -471,10 +533,7 @@ class AltDiffusionImg2ImgPipeline(
         return image, has_nsfw_concept
 
     def decode_latents(self, latents):
-        deprecation_message = (
-            "The decode_latents method is deprecated and will be removed in 1.0.0. Please use"
-            " VaeImageProcessor.postprocess(...) instead"
-        )
+        deprecation_message = "The decode_latents method is deprecated and will be removed in 1.0.0. Please use VaeImageProcessor.postprocess(...) instead"
         deprecate("decode_latents", "1.0.0", deprecation_message, standard_warn=False)
 
         latents = 1 / self.vae.config.scaling_factor * latents
@@ -524,8 +583,7 @@ class AltDiffusionImg2ImgPipeline(
             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"
-                f" {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"
+                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(
@@ -578,8 +636,8 @@ class AltDiffusionImg2ImgPipeline(
         else:
             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"
-                    f" batch size of {batch_size}. Make sure the batch size matches the length of the generators."
+                    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."
                 )
 
             elif isinstance(generator, list):
@@ -705,6 +763,7 @@ class AltDiffusionImg2ImgPipeline(
         image: PipelineImageInput = None,
         strength: float = 0.8,
         num_inference_steps: Optional[int] = 50,
+        timesteps: List[int] = None,
         guidance_scale: Optional[float] = 7.5,
         negative_prompt: Optional[Union[str, List[str]]] = None,
         num_images_per_prompt: Optional[int] = 1,
@@ -712,6 +771,7 @@ class AltDiffusionImg2ImgPipeline(
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
         prompt_embeds: Optional[torch.FloatTensor] = None,
         negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        ip_adapter_image: Optional[PipelineImageInput] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
@@ -741,6 +801,10 @@ class AltDiffusionImg2ImgPipeline(
             num_inference_steps (`int`, *optional*, defaults to 50):
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference. This parameter is modulated by `strength`.
+            timesteps (`List[int]`, *optional*):
+                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
+                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
+                passed will be used. Must be in descending order.
             guidance_scale (`float`, *optional*, defaults to 7.5):
                 A higher guidance scale value encourages the model to generate images closely linked to the text
                 `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
@@ -761,6 +825,7 @@ class AltDiffusionImg2ImgPipeline(
             negative_prompt_embeds (`torch.FloatTensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
+            ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             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`):
@@ -780,7 +845,7 @@ class AltDiffusionImg2ImgPipeline(
             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 pipeine class.
+                `._callback_tensor_inputs` attribute of your pipeline class.
         Examples:
 
         Returns:
@@ -798,15 +863,13 @@ class AltDiffusionImg2ImgPipeline(
             deprecate(
                 "callback",
                 "1.0.0",
-                "Passing `callback` as an input argument to `__call__` is deprecated, consider use"
-                " `callback_on_step_end`",
+                "Passing `callback` as an input argument to `__call__` is deprecated, consider use `callback_on_step_end`",
             )
         if callback_steps is not None:
             deprecate(
                 "callback_steps",
                 "1.0.0",
-                "Passing `callback_steps` as an input argument to `__call__` is deprecated, consider use"
-                " `callback_on_step_end`",
+                "Passing `callback_steps` as an input argument to `__call__` is deprecated, consider use `callback_on_step_end`",
             )
 
         # 1. Check inputs. Raise error if not correct
@@ -855,11 +918,16 @@ class AltDiffusionImg2ImgPipeline(
         if self.do_classifier_free_guidance:
             prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
 
+        if ip_adapter_image is not None:
+            image_embeds, negative_image_embeds = self.encode_image(ip_adapter_image, device, num_images_per_prompt)
+            if self.do_classifier_free_guidance:
+                image_embeds = torch.cat([negative_image_embeds, image_embeds])
+
         # 4. Preprocess image
         image = self.image_processor.preprocess(image)
 
         # 5. set timesteps
-        self.scheduler.set_timesteps(num_inference_steps, device=device)
+        timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, timesteps)
         timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, strength, device)
         latent_timestep = timesteps[:1].repeat(batch_size * num_images_per_prompt)
 
@@ -877,7 +945,10 @@ class AltDiffusionImg2ImgPipeline(
         # 7. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
         extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
 
-        # 7.5 Optionally get Guidance Scale Embedding
+        # 7.1 Add image embeds for IP-Adapter
+        added_cond_kwargs = {"image_embeds": image_embeds} if ip_adapter_image is not None else None
+
+        # 7.2 Optionally get Guidance Scale Embedding
         timestep_cond = None
         if self.unet.config.time_cond_proj_dim is not None:
             guidance_scale_tensor = torch.tensor(self.guidance_scale - 1).repeat(batch_size * num_images_per_prompt)
@@ -901,6 +972,7 @@ class AltDiffusionImg2ImgPipeline(
                     encoder_hidden_states=prompt_embeds,
                     timestep_cond=timestep_cond,
                     cross_attention_kwargs=self.cross_attention_kwargs,
+                    added_cond_kwargs=added_cond_kwargs,
                     return_dict=False,
                 )[0]
 

diffusers/pipelines/animatediff/pipeline_animatediff.py

@@ -18,10 +18,10 @@ from typing import Any, Callable, Dict, List, Optional, Union
 
 import numpy as np
 import torch
-from transformers import CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
 
-from ...image_processor import VaeImageProcessor
-from ...loaders import LoraLoaderMixin, TextualInversionLoaderMixin
+from ...image_processor import PipelineImageInput, VaeImageProcessor
+from ...loaders import IPAdapterMixin, LoraLoaderMixin, TextualInversionLoaderMixin
 from ...models import AutoencoderKL, UNet2DConditionModel, UNetMotionModel
 from ...models.lora import adjust_lora_scale_text_encoder
 from ...models.unet_motion_model import MotionAdapter
@@ -77,7 +77,7 @@ class AnimateDiffPipelineOutput(BaseOutput):
     frames: Union[torch.Tensor, np.ndarray]
 
 
-class AnimateDiffPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLoaderMixin):
+class AnimateDiffPipeline(DiffusionPipeline, TextualInversionLoaderMixin, IPAdapterMixin, LoraLoaderMixin):
     r"""
     Pipeline for text-to-video generation.
 
@@ -99,7 +99,9 @@ class AnimateDiffPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLo
             A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
     """
+
     model_cpu_offload_seq = "text_encoder->unet->vae"
+    _optional_components = ["feature_extractor", "image_encoder"]
 
     def __init__(
         self,
@@ -116,6 +118,8 @@ class AnimateDiffPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLo
             EulerAncestralDiscreteScheduler,
             DPMSolverMultistepScheduler,
         ],
+        feature_extractor: CLIPImageProcessor = None,
+        image_encoder: CLIPVisionModelWithProjection = None,
     ):
         super().__init__()
         unet = UNetMotionModel.from_unet2d(unet, motion_adapter)
@@ -127,6 +131,8 @@ class AnimateDiffPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLo
             unet=unet,
             motion_adapter=motion_adapter,
             scheduler=scheduler,
+            feature_extractor=feature_extractor,
+            image_encoder=image_encoder,
         )
         self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
@@ -313,6 +319,20 @@ class AnimateDiffPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLo
 
         return prompt_embeds, negative_prompt_embeds
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
+    def encode_image(self, image, device, num_images_per_prompt):
+        dtype = next(self.image_encoder.parameters()).dtype
+
+        if not isinstance(image, torch.Tensor):
+            image = self.feature_extractor(image, return_tensors="pt").pixel_values
+
+        image = image.to(device=device, dtype=dtype)
+        image_embeds = self.image_encoder(image).image_embeds
+        image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
+
+        uncond_image_embeds = torch.zeros_like(image_embeds)
+        return image_embeds, uncond_image_embeds
+
     # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
     def decode_latents(self, latents):
         latents = 1 / self.vae.config.scaling_factor * latents
@@ -511,6 +531,7 @@ class AnimateDiffPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLo
         latents: Optional[torch.FloatTensor] = None,
         prompt_embeds: Optional[torch.FloatTensor] = None,
         negative_prompt_embeds: Optional[torch.FloatTensor] = None,
+        ip_adapter_image: Optional[PipelineImageInput] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
@@ -557,6 +578,7 @@ class AnimateDiffPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLo
             negative_prompt_embeds (`torch.FloatTensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
+            ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generated video. Choose between `torch.FloatTensor`, `PIL.Image` or
                 `np.array`.
@@ -628,6 +650,11 @@ class AnimateDiffPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLo
         if do_classifier_free_guidance:
             prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
 
+        if ip_adapter_image is not None:
+            image_embeds, negative_image_embeds = self.encode_image(ip_adapter_image, device, num_videos_per_prompt)
+            if do_classifier_free_guidance:
+                image_embeds = torch.cat([negative_image_embeds, image_embeds])
+
         # 4. Prepare timesteps
         self.scheduler.set_timesteps(num_inference_steps, device=device)
         timesteps = self.scheduler.timesteps
@@ -648,6 +675,8 @@ class AnimateDiffPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLo
 
         # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
         extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
+        # 7 Add image embeds for IP-Adapter
+        added_cond_kwargs = {"image_embeds": image_embeds} if ip_adapter_image is not None else None
 
         # Denoising loop
         num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
@@ -663,6 +692,7 @@ class AnimateDiffPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLo
                     t,
                     encoder_hidden_states=prompt_embeds,
                     cross_attention_kwargs=cross_attention_kwargs,
+                    added_cond_kwargs=added_cond_kwargs,
                 ).sample
 
                 # perform guidance

diffusers/pipelines/audioldm/pipeline_audioldm.py

@@ -72,6 +72,7 @@ class AudioLDMPipeline(DiffusionPipeline):
         vocoder ([`~transformers.SpeechT5HifiGan`]):
             Vocoder of class `SpeechT5HifiGan`.
     """
+
     model_cpu_offload_seq = "text_encoder->unet->vae"
 
     def __init__(

diffusers/pipelines/auto_pipeline.py

@@ -42,6 +42,7 @@ from .kandinsky2_2 import (
     KandinskyV22InpaintPipeline,
     KandinskyV22Pipeline,
 )
+from .kandinsky3 import Kandinsky3Img2ImgPipeline, Kandinsky3Pipeline
 from .latent_consistency_models import LatentConsistencyModelImg2ImgPipeline, LatentConsistencyModelPipeline
 from .pixart_alpha import PixArtAlphaPipeline
 from .stable_diffusion import (
@@ -64,6 +65,7 @@ AUTO_TEXT2IMAGE_PIPELINES_MAPPING = OrderedDict(
         ("if", IFPipeline),
         ("kandinsky", KandinskyCombinedPipeline),
         ("kandinsky22", KandinskyV22CombinedPipeline),
+        ("kandinsky3", Kandinsky3Pipeline),
         ("stable-diffusion-controlnet", StableDiffusionControlNetPipeline),
         ("stable-diffusion-xl-controlnet", StableDiffusionXLControlNetPipeline),
         ("wuerstchen", WuerstchenCombinedPipeline),
@@ -79,6 +81,7 @@ AUTO_IMAGE2IMAGE_PIPELINES_MAPPING = OrderedDict(
         ("if", IFImg2ImgPipeline),
         ("kandinsky", KandinskyImg2ImgCombinedPipeline),
         ("kandinsky22", KandinskyV22Img2ImgCombinedPipeline),
+        ("kandinsky3", Kandinsky3Img2ImgPipeline),
         ("stable-diffusion-controlnet", StableDiffusionControlNetImg2ImgPipeline),
         ("stable-diffusion-xl-controlnet", StableDiffusionXLControlNetImg2ImgPipeline),
         ("lcm", LatentConsistencyModelImg2ImgPipeline),
@@ -181,6 +184,7 @@ class AutoPipelineForText2Image(ConfigMixin):
           diffusion pipeline's components.
 
     """
+
     config_name = "model_index.json"
 
     def __init__(self, *args, **kwargs):
@@ -451,6 +455,7 @@ class AutoPipelineForImage2Image(ConfigMixin):
           diffusion pipeline's components.
 
     """
+
     config_name = "model_index.json"
 
     def __init__(self, *args, **kwargs):
@@ -726,6 +731,7 @@ class AutoPipelineForInpainting(ConfigMixin):
           diffusion pipeline's components.
 
     """
+
     config_name = "model_index.json"
 
     def __init__(self, *args, **kwargs):

diffusers/pipelines/consistency_models/pipeline_consistency_models.py

@@ -74,6 +74,7 @@ class ConsistencyModelPipeline(DiffusionPipeline):
             A scheduler to be used in combination with `unet` to denoise the encoded image latents. Currently only
             compatible with [`CMStochasticIterativeScheduler`].
     """
+
     model_cpu_offload_seq = "unet"
 
     def __init__(self, unet: UNet2DModel, scheduler: CMStochasticIterativeScheduler) -> None: