diffusers 0.33.0__py3-none-any.whl → 0.34.0__py3-none-any.whl

diffusers/pipelines/__init__.py

@@ -148,6 +148,7 @@ else:
         "AudioLDM2UNet2DConditionModel",
     ]
     _import_structure["blip_diffusion"] = ["BlipDiffusionPipeline"]
+    _import_structure["chroma"] = ["ChromaPipeline", "ChromaImg2ImgPipeline"]
     _import_structure["cogvideo"] = [
         "CogVideoXPipeline",
         "CogVideoXImageToVideoPipeline",
@@ -156,6 +157,13 @@ else:
     ]
     _import_structure["cogview3"] = ["CogView3PlusPipeline"]
     _import_structure["cogview4"] = ["CogView4Pipeline", "CogView4ControlPipeline"]
+    _import_structure["consisid"] = ["ConsisIDPipeline"]
+    _import_structure["cosmos"] = [
+        "Cosmos2TextToImagePipeline",
+        "CosmosTextToWorldPipeline",
+        "CosmosVideoToWorldPipeline",
+        "Cosmos2VideoToWorldPipeline",
+    ]
     _import_structure["controlnet"].extend(
         [
             "BlipDiffusionControlNetPipeline",
@@ -221,11 +229,13 @@ else:
         "EasyAnimateInpaintPipeline",
         "EasyAnimateControlPipeline",
     ]
+    _import_structure["hidream_image"] = ["HiDreamImagePipeline"]
     _import_structure["hunyuandit"] = ["HunyuanDiTPipeline"]
     _import_structure["hunyuan_video"] = [
         "HunyuanVideoPipeline",
         "HunyuanSkyreelsImageToVideoPipeline",
         "HunyuanVideoImageToVideoPipeline",
+        "HunyuanVideoFramepackPipeline",
     ]
     _import_structure["kandinsky"] = [
         "KandinskyCombinedPipeline",
@@ -264,7 +274,12 @@ else:
         ]
     )
     _import_structure["latte"] = ["LattePipeline"]
-    _import_structure["ltx"] = ["LTXPipeline", "LTXImageToVideoPipeline", "LTXConditionPipeline"]
+    _import_structure["ltx"] = [
+        "LTXPipeline",
+        "LTXImageToVideoPipeline",
+        "LTXConditionPipeline",
+        "LTXLatentUpsamplePipeline",
+    ]
     _import_structure["lumina"] = ["LuminaPipeline", "LuminaText2ImgPipeline"]
     _import_structure["lumina2"] = ["Lumina2Pipeline", "Lumina2Text2ImgPipeline"]
     _import_structure["marigold"].extend(
@@ -277,10 +292,16 @@ else:
     _import_structure["mochi"] = ["MochiPipeline"]
     _import_structure["musicldm"] = ["MusicLDMPipeline"]
     _import_structure["omnigen"] = ["OmniGenPipeline"]
+    _import_structure["visualcloze"] = ["VisualClozePipeline", "VisualClozeGenerationPipeline"]
     _import_structure["paint_by_example"] = ["PaintByExamplePipeline"]
     _import_structure["pia"] = ["PIAPipeline"]
     _import_structure["pixart_alpha"] = ["PixArtAlphaPipeline", "PixArtSigmaPipeline"]
-    _import_structure["sana"] = ["SanaPipeline", "SanaSprintPipeline"]
+    _import_structure["sana"] = [
+        "SanaPipeline",
+        "SanaSprintPipeline",
+        "SanaControlNetPipeline",
+        "SanaSprintImg2ImgPipeline",
+    ]
     _import_structure["semantic_stable_diffusion"] = ["SemanticStableDiffusionPipeline"]
     _import_structure["shap_e"] = ["ShapEImg2ImgPipeline", "ShapEPipeline"]
     _import_structure["stable_audio"] = [
@@ -356,7 +377,7 @@ else:
         "WuerstchenDecoderPipeline",
         "WuerstchenPriorPipeline",
     ]
-    _import_structure["wan"] = ["WanPipeline", "WanImageToVideoPipeline", "WanVideoToVideoPipeline"]
+    _import_structure["wan"] = ["WanPipeline", "WanImageToVideoPipeline", "WanVideoToVideoPipeline", "WanVACEPipeline"]
 try:
     if not is_onnx_available():
         raise OptionalDependencyNotAvailable()
@@ -516,6 +537,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         )
         from .aura_flow import AuraFlowPipeline
         from .blip_diffusion import BlipDiffusionPipeline
+        from .chroma import ChromaImg2ImgPipeline, ChromaPipeline
         from .cogvideo import (
             CogVideoXFunControlPipeline,
             CogVideoXImageToVideoPipeline,
@@ -544,6 +566,12 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusionControlNetXSPipeline,
             StableDiffusionXLControlNetXSPipeline,
         )
+        from .cosmos import (
+            Cosmos2TextToImagePipeline,
+            Cosmos2VideoToWorldPipeline,
+            CosmosTextToWorldPipeline,
+            CosmosVideoToWorldPipeline,
+        )
         from .deepfloyd_if import (
             IFImg2ImgPipeline,
             IFImg2ImgSuperResolutionPipeline,
@@ -585,8 +613,10 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             FluxPriorReduxPipeline,
             ReduxImageEncoder,
         )
+        from .hidream_image import HiDreamImagePipeline
         from .hunyuan_video import (
             HunyuanSkyreelsImageToVideoPipeline,
+            HunyuanVideoFramepackPipeline,
             HunyuanVideoImageToVideoPipeline,
             HunyuanVideoPipeline,
         )
@@ -629,7 +659,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             LEditsPPPipelineStableDiffusion,
             LEditsPPPipelineStableDiffusionXL,
         )
-        from .ltx import LTXConditionPipeline, LTXImageToVideoPipeline, LTXPipeline
+        from .ltx import LTXConditionPipeline, LTXImageToVideoPipeline, LTXLatentUpsamplePipeline, LTXPipeline
         from .lumina import LuminaPipeline, LuminaText2ImgPipeline
         from .lumina2 import Lumina2Pipeline, Lumina2Text2ImgPipeline
         from .marigold import (
@@ -662,7 +692,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from .paint_by_example import PaintByExamplePipeline
         from .pia import PIAPipeline
         from .pixart_alpha import PixArtAlphaPipeline, PixArtSigmaPipeline
-        from .sana import SanaPipeline, SanaSprintPipeline
+        from .sana import SanaControlNetPipeline, SanaPipeline, SanaSprintImg2ImgPipeline, SanaSprintPipeline
         from .semantic_stable_diffusion import SemanticStableDiffusionPipeline
         from .shap_e import ShapEImg2ImgPipeline, ShapEPipeline
         from .stable_audio import StableAudioPipeline, StableAudioProjectionModel
@@ -720,7 +750,8 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             UniDiffuserPipeline,
             UniDiffuserTextDecoder,
         )
-        from .wan import WanImageToVideoPipeline, WanPipeline, WanVideoToVideoPipeline
+        from .visualcloze import VisualClozeGenerationPipeline, VisualClozePipeline
+        from .wan import WanImageToVideoPipeline, WanPipeline, WanVACEPipeline, WanVideoToVideoPipeline
         from .wuerstchen import (
             WuerstchenCombinedPipeline,
             WuerstchenDecoderPipeline,

diffusers/pipelines/allegro/pipeline_allegro.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The RhymesAI and The HuggingFace Team.
+# Copyright 2025 The RhymesAI and The HuggingFace Team.
 # All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -351,7 +351,7 @@ class AllegroPipeline(DiffusionPipeline):
     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
+        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
         # and should be between [0, 1]
 
         accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
@@ -514,7 +514,7 @@ class AllegroPipeline(DiffusionPipeline):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
@@ -738,11 +738,11 @@ class AllegroPipeline(DiffusionPipeline):
                 Custom timesteps to use for the denoising process. If not defined, equal spaced `num_inference_steps`
                 timesteps are used. Must be in descending order.
             guidance_scale (`float`, *optional*, defaults to 7.5):
-                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 videos that are closely linked to the text `prompt`,
-                usually at the expense of lower video quality.
+                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 videos that are closely linked to
+                the text `prompt`, usually at the expense of lower video quality.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of videos to generate per prompt.
             num_frames: (`int`, *optional*, defaults to 88):
@@ -752,8 +752,8 @@ class AllegroPipeline(DiffusionPipeline):
             width (`int`, *optional*, defaults to self.unet.config.sample_size):
                 The width in pixels of the generated video.
             eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
-                [`schedulers.DDIMScheduler`], will be ignored for others.
+                Corresponds to parameter eta (η) in the DDIM paper: https://huggingface.co/papers/2010.02502. Only
+                applies to [`schedulers.DDIMScheduler`], will be ignored for others.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
@@ -833,7 +833,7 @@ class AllegroPipeline(DiffusionPipeline):
         device = self._execution_device
 
         # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+        # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
         # corresponds to doing no classifier free guidance.
         do_classifier_free_guidance = guidance_scale > 1.0
 

diffusers/pipelines/amused/pipeline_amused.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 The HuggingFace 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.
@@ -21,7 +21,7 @@ from ...image_processor import VaeImageProcessor
 from ...models import UVit2DModel, VQModel
 from ...schedulers import AmusedScheduler
 from ...utils import is_torch_xla_available, replace_example_docstring
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from ..pipeline_utils import DeprecatedPipelineMixin, DiffusionPipeline, ImagePipelineOutput
 
 
 if is_torch_xla_available():
@@ -47,7 +47,8 @@ EXAMPLE_DOC_STRING = """
 """
 
 
-class AmusedPipeline(DiffusionPipeline):
+class AmusedPipeline(DeprecatedPipelineMixin, DiffusionPipeline):
+    _last_supported_version = "0.33.1"
     image_processor: VaeImageProcessor
     vqvae: VQModel
     tokenizer: CLIPTokenizer
@@ -131,7 +132,7 @@ class AmusedPipeline(DiffusionPipeline):
                 generation deterministic.
             latents (`torch.IntTensor`, *optional*):
                 Pre-generated tokens representing latent vectors in `self.vqvae`, to be used as inputs for image
-                gneration. If not provided, the starting latents will be completely masked.
+                generation. If not provided, the starting latents will be completely masked.
             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. A single vector from the
@@ -160,10 +161,10 @@ class AmusedPipeline(DiffusionPipeline):
             micro_conditioning_aesthetic_score (`int`, *optional*, defaults to 6):
                 The targeted aesthetic score according to the laion aesthetic classifier. See
                 https://laion.ai/blog/laion-aesthetics/ and the micro-conditioning section of
-                https://arxiv.org/abs/2307.01952.
+                https://huggingface.co/papers/2307.01952.
             micro_conditioning_crop_coord (`Tuple[int]`, *optional*, defaults to (0, 0)):
                 The targeted height, width crop coordinates. See the micro-conditioning section of
-                https://arxiv.org/abs/2307.01952.
+                https://huggingface.co/papers/2307.01952.
             temperature (`Union[int, Tuple[int, int], List[int]]`, *optional*, defaults to (2, 0)):
                 Configures the temperature scheduler on `self.scheduler` see `AmusedScheduler#set_timesteps`.
 

diffusers/pipelines/amused/pipeline_amused_img2img.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 The HuggingFace 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.
@@ -21,7 +21,7 @@ from ...image_processor import PipelineImageInput, VaeImageProcessor
 from ...models import UVit2DModel, VQModel
 from ...schedulers import AmusedScheduler
 from ...utils import is_torch_xla_available, replace_example_docstring
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from ..pipeline_utils import DeprecatedPipelineMixin, DiffusionPipeline, ImagePipelineOutput
 
 
 if is_torch_xla_available():
@@ -57,7 +57,8 @@ EXAMPLE_DOC_STRING = """
 """
 
 
-class AmusedImg2ImgPipeline(DiffusionPipeline):
+class AmusedImg2ImgPipeline(DeprecatedPipelineMixin, DiffusionPipeline):
+    _last_supported_version = "0.33.1"
     image_processor: VaeImageProcessor
     vqvae: VQModel
     tokenizer: CLIPTokenizer
@@ -179,10 +180,10 @@ class AmusedImg2ImgPipeline(DiffusionPipeline):
             micro_conditioning_aesthetic_score (`int`, *optional*, defaults to 6):
                 The targeted aesthetic score according to the laion aesthetic classifier. See
                 https://laion.ai/blog/laion-aesthetics/ and the micro-conditioning section of
-                https://arxiv.org/abs/2307.01952.
+                https://huggingface.co/papers/2307.01952.
             micro_conditioning_crop_coord (`Tuple[int]`, *optional*, defaults to (0, 0)):
                 The targeted height, width crop coordinates. See the micro-conditioning section of
-                https://arxiv.org/abs/2307.01952.
+                https://huggingface.co/papers/2307.01952.
             temperature (`Union[int, Tuple[int, int], List[int]]`, *optional*, defaults to (2, 0)):
                 Configures the temperature scheduler on `self.scheduler` see `AmusedScheduler#set_timesteps`.
 

diffusers/pipelines/amused/pipeline_amused_inpaint.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 The HuggingFace 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.
@@ -22,7 +22,7 @@ from ...image_processor import PipelineImageInput, VaeImageProcessor
 from ...models import UVit2DModel, VQModel
 from ...schedulers import AmusedScheduler
 from ...utils import is_torch_xla_available, replace_example_docstring
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from ..pipeline_utils import DeprecatedPipelineMixin, DiffusionPipeline, ImagePipelineOutput
 
 
 if is_torch_xla_available():
@@ -65,7 +65,8 @@ EXAMPLE_DOC_STRING = """
 """
 
 
-class AmusedInpaintPipeline(DiffusionPipeline):
+class AmusedInpaintPipeline(DeprecatedPipelineMixin, DiffusionPipeline):
+    _last_supported_version = "0.33.1"
     image_processor: VaeImageProcessor
     vqvae: VQModel
     tokenizer: CLIPTokenizer
@@ -203,10 +204,10 @@ class AmusedInpaintPipeline(DiffusionPipeline):
             micro_conditioning_aesthetic_score (`int`, *optional*, defaults to 6):
                 The targeted aesthetic score according to the laion aesthetic classifier. See
                 https://laion.ai/blog/laion-aesthetics/ and the micro-conditioning section of
-                https://arxiv.org/abs/2307.01952.
+                https://huggingface.co/papers/2307.01952.
             micro_conditioning_crop_coord (`Tuple[int]`, *optional*, defaults to (0, 0)):
                 The targeted height, width crop coordinates. See the micro-conditioning section of
-                https://arxiv.org/abs/2307.01952.
+                https://huggingface.co/papers/2307.01952.
             temperature (`Union[int, Tuple[int, int], List[int]]`, *optional*, defaults to (2, 0)):
                 Configures the temperature scheduler on `self.scheduler` see `AmusedScheduler#set_timesteps`.
 

diffusers/pipelines/animatediff/pipeline_animatediff.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 The HuggingFace 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.
@@ -428,7 +428,7 @@ class AnimateDiffPipeline(
     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
+        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
         # and should be between [0, 1]
 
         accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
@@ -514,7 +514,7 @@ class AnimateDiffPipeline(
     def prepare_latents(
         self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents=None
     ):
-        # If FreeNoise is enabled, generate latents as described in Equation (7) of [FreeNoise](https://arxiv.org/abs/2310.15169)
+        # If FreeNoise is enabled, generate latents as described in Equation (7) of [FreeNoise](https://huggingface.co/papers/2310.15169)
         if self.free_noise_enabled:
             latents = self._prepare_latents_free_noise(
                 batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents
@@ -552,7 +552,7 @@ class AnimateDiffPipeline(
         return self._clip_skip
 
     # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+    # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
     # corresponds to doing no classifier free guidance.
     @property
     def do_classifier_free_guidance(self):
@@ -621,8 +621,8 @@ class AnimateDiffPipeline(
                 The prompt or prompts to guide what to not include in image generation. If not defined, you need to
                 pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
             eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
-                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
+                Corresponds to parameter eta (η) from the [DDIM](https://huggingface.co/papers/2010.02502) paper. Only
+                applies to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                 generation deterministic.

diffusers/pipelines/animatediff/pipeline_animatediff_controlnet.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 The HuggingFace 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.
@@ -472,7 +472,7 @@ class AnimateDiffControlNetPipeline(
     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
+        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
         # and should be between [0, 1]
 
         accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
@@ -630,7 +630,7 @@ class AnimateDiffControlNetPipeline(
     def prepare_latents(
         self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents=None
     ):
-        # If FreeNoise is enabled, generate latents as described in Equation (7) of [FreeNoise](https://arxiv.org/abs/2310.15169)
+        # If FreeNoise is enabled, generate latents as described in Equation (7) of [FreeNoise](https://huggingface.co/papers/2310.15169)
         if self.free_noise_enabled:
             latents = self._prepare_latents_free_noise(
                 batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents
@@ -700,7 +700,7 @@ class AnimateDiffControlNetPipeline(
         return self._clip_skip
 
     # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+    # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
     # corresponds to doing no classifier free guidance.
     @property
     def do_classifier_free_guidance(self):
@@ -772,8 +772,8 @@ class AnimateDiffControlNetPipeline(
                 The prompt or prompts to guide what to not include in image generation. If not defined, you need to
                 pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
             eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
-                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
+                Corresponds to parameter eta (η) from the [DDIM](https://huggingface.co/papers/2010.02502) paper. Only
+                applies to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                 generation deterministic.

diffusers/pipelines/animatediff/pipeline_animatediff_sdxl.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 The HuggingFace 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.
@@ -125,7 +125,7 @@ def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
     r"""
     Rescales `noise_cfg` tensor based on `guidance_rescale` to improve image quality and fix overexposure. Based on
     Section 3.4 from [Common Diffusion Noise Schedules and Sample Steps are
-    Flawed](https://arxiv.org/pdf/2305.08891.pdf).
+    Flawed](https://huggingface.co/papers/2305.08891).
 
     Args:
         noise_cfg (`torch.Tensor`):
@@ -652,7 +652,7 @@ class AnimateDiffSDXLPipeline(
     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
+        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
         # and should be between [0, 1]
 
         accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
@@ -844,7 +844,7 @@ class AnimateDiffSDXLPipeline(
         return self._clip_skip
 
     # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+    # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
     # corresponds to doing no classifier free guidance.
     @property
     def do_classifier_free_guidance(self):
@@ -948,11 +948,11 @@ class AnimateDiffSDXLPipeline(
                 "Mixture of Denoisers" multi-pipeline setup, as elaborated in [**Refining the Image
                 Output**](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl#refining-the-image-output)
             guidance_scale (`float`, *optional*, 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 video quality.
+                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 video quality.
             negative_prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts not to guide the video generation. If not defined, one has to pass
                 `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
@@ -963,8 +963,8 @@ class AnimateDiffSDXLPipeline(
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of videos to generate per prompt.
             eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
-                [`schedulers.DDIMScheduler`], will be ignored for others.
+                Corresponds to parameter eta (η) in the DDIM paper: https://huggingface.co/papers/2010.02502. Only
+                applies to [`schedulers.DDIMScheduler`], will be ignored for others.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
@@ -1003,9 +1003,10 @@ class AnimateDiffSDXLPipeline(
                 [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
             guidance_rescale (`float`, *optional*, defaults to 0.0):
                 Guidance rescale factor proposed by [Common Diffusion Noise Schedules and Sample Steps are
-                Flawed](https://arxiv.org/pdf/2305.08891.pdf) `guidance_scale` is defined as `φ` in equation 16. of
-                [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf).
-                Guidance rescale factor should fix overexposure when using zero terminal SNR.
+                Flawed](https://huggingface.co/papers/2305.08891) `guidance_scale` is defined as `φ` in equation 16. of
+                [Common Diffusion Noise Schedules and Sample Steps are
+                Flawed](https://huggingface.co/papers/2305.08891). Guidance rescale factor should fix overexposure when
+                using zero terminal SNR.
             original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
                 `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
@@ -1252,7 +1253,7 @@ class AnimateDiffSDXLPipeline(
                         noise_pred = noise_pred_uncond + self.guidance_scale * (noise_pred_text - noise_pred_uncond)
 
                     if self.do_classifier_free_guidance and self.guidance_rescale > 0.0:
-                        # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
+                        # Based on 3.4. in https://huggingface.co/papers/2305.08891
                         noise_pred = rescale_noise_cfg(
                             noise_pred, noise_pred_text, guidance_rescale=self.guidance_rescale
                         )

diffusers/pipelines/animatediff/pipeline_animatediff_sparsectrl.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 The HuggingFace 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.
@@ -140,7 +140,7 @@ class AnimateDiffSparseControlNetPipeline(
 ):
     r"""
     Pipeline for controlled text-to-video generation using the method described in [SparseCtrl: Adding Sparse Controls
-    to Text-to-Video Diffusion Models](https://arxiv.org/abs/2311.16933).
+    to Text-to-Video Diffusion Models](https://huggingface.co/papers/2311.16933).
 
     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.).
@@ -475,7 +475,7 @@ class AnimateDiffSparseControlNetPipeline(
     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
+        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
         # and should be between [0, 1]
 
         accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
@@ -695,7 +695,7 @@ class AnimateDiffSparseControlNetPipeline(
         return self._clip_skip
 
     # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+    # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
     # corresponds to doing no classifier free guidance.
     @property
     def do_classifier_free_guidance(self):
@@ -762,8 +762,8 @@ class AnimateDiffSparseControlNetPipeline(
                 The prompt or prompts to guide what to not include in image generation. If not defined, you need to
                 pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
             eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
-                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
+                Corresponds to parameter eta (η) from the [DDIM](https://huggingface.co/papers/2010.02502) paper. Only
+                applies to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                 generation deterministic.

diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 The HuggingFace 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.
@@ -539,7 +539,7 @@ class AnimateDiffVideoToVideoPipeline(
     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
+        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
         # and should be between [0, 1]
 
         accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
@@ -725,7 +725,7 @@ class AnimateDiffVideoToVideoPipeline(
         return self._clip_skip
 
     # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+    # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
     # corresponds to doing no classifier free guidance.
     @property
     def do_classifier_free_guidance(self):
@@ -805,8 +805,8 @@ class AnimateDiffVideoToVideoPipeline(
                 The prompt or prompts to guide what to not include in image generation. If not defined, you need to
                 pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
             eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
-                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
+                Corresponds to parameter eta (η) from the [DDIM](https://huggingface.co/papers/2010.02502) paper. Only
+                applies to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                 generation deterministic.

diffusers/pipelines/animatediff/pipeline_animatediff_video2video_controlnet.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 The HuggingFace 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.
@@ -571,7 +571,7 @@ class AnimateDiffVideoToVideoControlNetPipeline(
     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
+        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
         # and should be between [0, 1]
 
         accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
@@ -890,7 +890,7 @@ class AnimateDiffVideoToVideoControlNetPipeline(
         return self._clip_skip
 
     # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+    # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
     # corresponds to doing no classifier free guidance.
     @property
     def do_classifier_free_guidance(self):
@@ -975,8 +975,8 @@ class AnimateDiffVideoToVideoControlNetPipeline(
                 The prompt or prompts to guide what to not include in image generation. If not defined, you need to
                 pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
             eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
-                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
+                Corresponds to parameter eta (η) from the [DDIM](https://huggingface.co/papers/2010.02502) paper. Only
+                applies to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                 generation deterministic.