diffusers 0.33.1__py3-none-any.whl → 0.34.0__py3-none-any.whl

diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth.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.
@@ -33,7 +33,7 @@ from ...utils import (
 )
 from ...utils.torch_utils import randn_tensor
 from ...video_processor import VideoProcessor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ..pipeline_utils import DeprecatedPipelineMixin, DiffusionPipeline, StableDiffusionMixin
 from . import TextToVideoSDPipelineOutput
 
 
@@ -68,8 +68,13 @@ EXAMPLE_DOC_STRING = """
 
 
 class TextToVideoSDPipeline(
-    DiffusionPipeline, StableDiffusionMixin, TextualInversionLoaderMixin, StableDiffusionLoraLoaderMixin
+    DeprecatedPipelineMixin,
+    DiffusionPipeline,
+    StableDiffusionMixin,
+    TextualInversionLoaderMixin,
+    StableDiffusionLoraLoaderMixin,
 ):
+    _last_supported_version = "0.33.1"
     r"""
     Pipeline for text-to-video generation.
 
@@ -349,7 +354,7 @@ class TextToVideoSDPipeline(
     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())
@@ -489,8 +494,8 @@ class TextToVideoSDPipeline(
             num_images_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             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.
@@ -550,7 +555,7 @@ class TextToVideoSDPipeline(
 
         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/text_to_video_synthesis/pipeline_text_to_video_synth_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.
@@ -34,7 +34,7 @@ from ...utils import (
 )
 from ...utils.torch_utils import randn_tensor
 from ...video_processor import VideoProcessor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ..pipeline_utils import DeprecatedPipelineMixin, DiffusionPipeline, StableDiffusionMixin
 from . import TextToVideoSDPipelineOutput
 
 
@@ -103,8 +103,13 @@ def retrieve_latents(
 
 
 class VideoToVideoSDPipeline(
-    DiffusionPipeline, StableDiffusionMixin, TextualInversionLoaderMixin, StableDiffusionLoraLoaderMixin
+    DeprecatedPipelineMixin,
+    DiffusionPipeline,
+    StableDiffusionMixin,
+    TextualInversionLoaderMixin,
+    StableDiffusionLoraLoaderMixin,
 ):
+    _last_supported_version = "0.33.1"
     r"""
     Pipeline for text-guided video-to-video generation.
 
@@ -385,7 +390,7 @@ class VideoToVideoSDPipeline(
     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())
@@ -553,8 +558,8 @@ class VideoToVideoSDPipeline(
                 The prompt or prompts to guide what to not include in video 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.
@@ -609,7 +614,7 @@ class VideoToVideoSDPipeline(
 
         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/text_to_video_synthesis/pipeline_text_to_video_zero.py

@@ -23,8 +23,8 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...utils.torch_utils import empty_device_cache, randn_tensor
+from ..pipeline_utils import DeprecatedPipelineMixin, DiffusionPipeline, StableDiffusionMixin
 from ..stable_diffusion import StableDiffusionSafetyChecker
 
 
@@ -296,12 +296,14 @@ def create_motion_field_and_warp_latents(motion_field_strength_x, motion_field_s
 
 
 class TextToVideoZeroPipeline(
+    DeprecatedPipelineMixin,
     DiffusionPipeline,
     StableDiffusionMixin,
     TextualInversionLoaderMixin,
     StableDiffusionLoraLoaderMixin,
     FromSingleFileMixin,
 ):
+    _last_supported_version = "0.33.1"
     r"""
     Pipeline for zero-shot text-to-video generation using Stable Diffusion.
 
@@ -588,8 +590,8 @@ class TextToVideoZeroPipeline(
             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) 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.
@@ -610,17 +612,17 @@ class TextToVideoZeroPipeline(
                 The frequency at which the `callback` function is called. If not specified, the callback is called at
                 every step.
             motion_field_strength_x (`float`, *optional*, defaults to 12):
-                Strength of motion in generated video along x-axis. See the [paper](https://arxiv.org/abs/2303.13439),
-                Sect. 3.3.1.
+                Strength of motion in generated video along x-axis. See the
+                [paper](https://huggingface.co/papers/2303.13439), Sect. 3.3.1.
             motion_field_strength_y (`float`, *optional*, defaults to 12):
-                Strength of motion in generated video along y-axis. See the [paper](https://arxiv.org/abs/2303.13439),
-                Sect. 3.3.1.
+                Strength of motion in generated video along y-axis. See the
+                [paper](https://huggingface.co/papers/2303.13439), Sect. 3.3.1.
             t0 (`int`, *optional*, defaults to 44):
                 Timestep t0. Should be in the range [0, num_inference_steps - 1]. See the
-                [paper](https://arxiv.org/abs/2303.13439), Sect. 3.3.1.
+                [paper](https://huggingface.co/papers/2303.13439), Sect. 3.3.1.
             t1 (`int`, *optional*, defaults to 47):
                 Timestep t0. Should be in the range [t0 + 1, num_inference_steps - 1]. See the
-                [paper](https://arxiv.org/abs/2303.13439), Sect. 3.3.1.
+                [paper](https://huggingface.co/papers/2303.13439), Sect. 3.3.1.
             frame_ids (`List[int]`, *optional*):
                 Indexes of the frames that are being generated. This is used when generating longer videos
                 chunk-by-chunk.
@@ -663,7 +665,7 @@ class TextToVideoZeroPipeline(
         batch_size = 1 if isinstance(prompt, str) else len(prompt)
         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
 
@@ -758,7 +760,7 @@ class TextToVideoZeroPipeline(
         # manually for max memory savings
         if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None:
             self.unet.to("cpu")
-        torch.cuda.empty_cache()
+        empty_device_cache()
 
         if output_type == "latent":
             image = latents
@@ -797,7 +799,7 @@ class TextToVideoZeroPipeline(
     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())

diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_zero_sdxl.py

@@ -35,7 +35,7 @@ from ...utils import (
     unscale_lora_layers,
 )
 from ...utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ..pipeline_utils import DeprecatedPipelineMixin, DiffusionPipeline, StableDiffusionMixin
 
 
 if is_invisible_watermark_available():
@@ -323,7 +323,7 @@ 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`):
@@ -346,11 +346,13 @@ def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
 
 
 class TextToVideoZeroSDXLPipeline(
+    DeprecatedPipelineMixin,
     DiffusionPipeline,
     StableDiffusionMixin,
     StableDiffusionXLLoraLoaderMixin,
     TextualInversionLoaderMixin,
 ):
+    _last_supported_version = "0.33.1"
     r"""
     Pipeline for zero-shot text-to-video generation using Stable Diffusion XL.
 
@@ -439,7 +441,7 @@ class TextToVideoZeroSDXLPipeline(
     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())
@@ -929,7 +931,7 @@ class TextToVideoZeroSDXLPipeline(
                     noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
 
                 if do_classifier_free_guidance and 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=guidance_rescale)
 
                 # compute the previous noisy sample x_t -> x_t-1
@@ -1009,11 +1011,11 @@ class TextToVideoZeroSDXLPipeline(
                 "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 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 images that are closely linked to the text `prompt`,
-                usually at the expense of lower image 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 image quality.
             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
@@ -1024,8 +1026,8 @@ class TextToVideoZeroSDXLPipeline(
             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.
@@ -1051,11 +1053,11 @@ class TextToVideoZeroSDXLPipeline(
                 generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                 tensor will ge generated by sampling using the supplied random `generator`.
             motion_field_strength_x (`float`, *optional*, defaults to 12):
-                Strength of motion in generated video along x-axis. See the [paper](https://arxiv.org/abs/2303.13439),
-                Sect. 3.3.1.
+                Strength of motion in generated video along x-axis. See the
+                [paper](https://huggingface.co/papers/2303.13439), Sect. 3.3.1.
             motion_field_strength_y (`float`, *optional*, defaults to 12):
-                Strength of motion in generated video along y-axis. See the [paper](https://arxiv.org/abs/2303.13439),
-                Sect. 3.3.1.
+                Strength of motion in generated video along y-axis. See the
+                [paper](https://huggingface.co/papers/2303.13439), Sect. 3.3.1.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
                 [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
@@ -1074,9 +1076,10 @@ class TextToVideoZeroSDXLPipeline(
                 [diffusers.cross_attention](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/cross_attention.py).
             guidance_rescale (`float`, *optional*, defaults to 0.7):
                 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 `(width, height)` if not specified. Part of SDXL's micro-conditioning as
@@ -1093,10 +1096,10 @@ class TextToVideoZeroSDXLPipeline(
                 section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
             t0 (`int`, *optional*, defaults to 44):
                 Timestep t0. Should be in the range [0, num_inference_steps - 1]. See the
-                [paper](https://arxiv.org/abs/2303.13439), Sect. 3.3.1.
+                [paper](https://huggingface.co/papers/2303.13439), Sect. 3.3.1.
             t1 (`int`, *optional*, defaults to 47):
                 Timestep t0. Should be in the range [t0 + 1, num_inference_steps - 1]. See the
-                [paper](https://arxiv.org/abs/2303.13439), Sect. 3.3.1.
+                [paper](https://huggingface.co/papers/2303.13439), Sect. 3.3.1.
 
         Returns:
             [`~pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.TextToVideoSDXLPipelineOutput`] or
@@ -1153,7 +1156,7 @@ class TextToVideoZeroSDXLPipeline(
         )
         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/unclip/pipeline_unclip.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Kakao Brain and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Kakao Brain and 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.
@@ -24,7 +24,7 @@ from ...models import PriorTransformer, UNet2DConditionModel, UNet2DModel
 from ...schedulers import UnCLIPScheduler
 from ...utils import is_torch_xla_available, logging
 from ...utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from ..pipeline_utils import DeprecatedPipelineMixin, DiffusionPipeline, ImagePipelineOutput
 from .text_proj import UnCLIPTextProjModel
 
 
@@ -38,7 +38,7 @@ else:
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
 
-class UnCLIPPipeline(DiffusionPipeline):
+class UnCLIPPipeline(DeprecatedPipelineMixin, DiffusionPipeline):
     """
     Pipeline for text-to-image generation using unCLIP.
 
@@ -69,6 +69,7 @@ class UnCLIPPipeline(DiffusionPipeline):
 
     """
 
+    _last_supported_version = "0.33.1"
     _exclude_from_cpu_offload = ["prior"]
 
     prior: PriorTransformer

diffusers/pipelines/unclip/pipeline_unclip_image_variation.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Kakao Brain and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Kakao Brain and 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.
@@ -29,7 +29,7 @@ from ...models import UNet2DConditionModel, UNet2DModel
 from ...schedulers import UnCLIPScheduler
 from ...utils import is_torch_xla_available, logging
 from ...utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from ..pipeline_utils import DeprecatedPipelineMixin, DiffusionPipeline, ImagePipelineOutput
 from .text_proj import UnCLIPTextProjModel
 
 
@@ -43,7 +43,7 @@ else:
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
 
-class UnCLIPImageVariationPipeline(DiffusionPipeline):
+class UnCLIPImageVariationPipeline(DeprecatedPipelineMixin, DiffusionPipeline):
     """
     Pipeline to generate image variations from an input image using UnCLIP.
 
@@ -73,6 +73,7 @@ class UnCLIPImageVariationPipeline(DiffusionPipeline):
             Scheduler used in the super resolution denoising process (a modified [`DDPMScheduler`]).
     """
 
+    _last_supported_version = "0.33.1"
     decoder: UNet2DConditionModel
     text_proj: UnCLIPTextProjModel
     text_encoder: CLIPTextModelWithProjection

diffusers/pipelines/unclip/text_proj.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Kakao Brain and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Kakao Brain and 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.
@@ -24,7 +24,7 @@ class UnCLIPTextProjModel(ModelMixin, ConfigMixin):
     Utility class for CLIP embeddings. Used to combine the image and text embeddings into a format usable by the
     decoder.
 
-    For more details, see the original paper: https://arxiv.org/abs/2204.06125 section 2.1
+    For more details, see the original paper: https://huggingface.co/papers/2204.06125 section 2.1
     """
 
     @register_to_config

diffusers/pipelines/unidiffuser/modeling_text_decoder.py

@@ -13,7 +13,7 @@ from ...models import ModelMixin
 # Modified from ClipCaptionModel in https://github.com/thu-ml/unidiffuser/blob/main/libs/caption_decoder.py
 class UniDiffuserTextDecoder(ModelMixin, ConfigMixin, ModuleUtilsMixin):
     """
-    Text decoder model for a image-text [UniDiffuser](https://arxiv.org/pdf/2303.06555.pdf) model. This is used to
+    Text decoder model for a image-text [UniDiffuser](https://huggingface.co/papers/2303.06555) model. This is used to
     generate text from the UniDiffuser image-text embedding.
 
     Parameters:
@@ -140,7 +140,7 @@ class UniDiffuserTextDecoder(ModelMixin, ConfigMixin, ModuleUtilsMixin):
             input_ids (`torch.Tensor` of shape `(N, max_seq_len)`):
                 Text tokens to use for inference.
             prefix_embeds (`torch.Tensor` of shape `(N, prefix_length, 768)`):
-                Prefix embedding to preprend to the embedded tokens.
+                Prefix embedding to prepend to the embedded tokens.
             attention_mask (`torch.Tensor` of shape `(N, prefix_length + max_seq_len, 768)`, *optional*):
                 Attention mask for the prefix embedding.
             labels (`torch.Tensor`, *optional*):

diffusers/pipelines/unidiffuser/modeling_uvit.py

@@ -832,7 +832,7 @@ class UTransformer2DModel(ModelMixin, ConfigMixin):
 
 class UniDiffuserModel(ModelMixin, ConfigMixin):
     """
-    Transformer model for a image-text [UniDiffuser](https://arxiv.org/pdf/2303.06555.pdf) model. This is a
+    Transformer model for a image-text [UniDiffuser](https://huggingface.co/papers/2303.06555) model. This is a
     modification of [`UTransformer2DModel`] with input and output heads for the VAE-embedded latent image, the
     CLIP-embedded image, and the CLIP-embedded prompt (see paper for more details).
 

diffusers/pipelines/unidiffuser/pipeline_unidiffuser.py

@@ -28,7 +28,7 @@ from ...utils import (
 )
 from ...utils.outputs import BaseOutput
 from ...utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline
+from ..pipeline_utils import DeprecatedPipelineMixin, DiffusionPipeline
 from .modeling_text_decoder import UniDiffuserTextDecoder
 from .modeling_uvit import UniDiffuserModel
 
@@ -62,7 +62,7 @@ class ImageTextPipelineOutput(BaseOutput):
     text: Optional[Union[List[str], List[List[str]]]]
 
 
-class UniDiffuserPipeline(DiffusionPipeline):
+class UniDiffuserPipeline(DeprecatedPipelineMixin, DiffusionPipeline):
     r"""
     Pipeline for a bimodal image-text model which supports unconditional text and image generation, text-conditioned
     image generation, image-conditioned text generation, and joint image-text generation.
@@ -96,6 +96,7 @@ class UniDiffuserPipeline(DiffusionPipeline):
             original UniDiffuser paper uses the [`DPMSolverMultistepScheduler`] scheduler.
     """
 
+    _last_supported_version = "0.33.1"
     # TODO: support for moving submodules for components with enable_model_cpu_offload
     model_cpu_offload_seq = "text_encoder->image_encoder->unet->vae->text_decoder"
 
@@ -153,7 +154,7 @@ class UniDiffuserPipeline(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())
@@ -803,7 +804,7 @@ class UniDiffuserPipeline(DiffusionPipeline):
 
     def _combine(self, img_vae, img_clip):
         r"""
-        Combines a latent iamge img_vae of shape (B, C, H, W) and a CLIP-embedded image img_clip of shape (B, 1,
+        Combines a latent image img_vae of shape (B, C, H, W) and a CLIP-embedded image img_clip of shape (B, 1,
         clip_img_dim) into a single tensor of shape (B, C * H * W + clip_img_dim).
         """
         img_vae = torch.reshape(img_vae, (img_vae.shape[0], -1))
@@ -1154,8 +1155,8 @@ class UniDiffuserPipeline(DiffusionPipeline):
                 `text` mode. If the mode is joint and both `num_images_per_prompt` and `num_prompts_per_image` are
                 supplied, `min(num_images_per_prompt, num_prompts_per_image)` samples are generated.
             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.
@@ -1243,7 +1244,7 @@ class UniDiffuserPipeline(DiffusionPipeline):
         reduce_text_emb_dim = self.text_intermediate_dim < self.text_encoder_hidden_size or self.mode != "text2img"
 
         # 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.
         # Note that this differs from the formulation in the unidiffusers paper!
         do_classifier_free_guidance = guidance_scale > 1.0

diffusers/pipelines/visualcloze/__init__.py

@@ -0,0 +1,52 @@
+from typing import TYPE_CHECKING
+
+from ...utils import (
+    DIFFUSERS_SLOW_IMPORT,
+    OptionalDependencyNotAvailable,
+    _LazyModule,
+    get_objects_from_module,
+    is_torch_available,
+    is_transformers_available,
+)
+
+
+_dummy_objects = {}
+_import_structure = {}
+
+
+try:
+    if not (is_transformers_available() and is_torch_available()):
+        raise OptionalDependencyNotAvailable()
+except OptionalDependencyNotAvailable:
+    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+
+    _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
+else:
+    _import_structure["pipeline_visualcloze_combined"] = ["VisualClozePipeline"]
+    _import_structure["pipeline_visualcloze_generation"] = ["VisualClozeGenerationPipeline"]
+
+
+if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
+    try:
+        if not (is_transformers_available() and is_torch_available()):
+            raise OptionalDependencyNotAvailable()
+
+    except OptionalDependencyNotAvailable:
+        from ...utils.dummy_torch_and_transformers_objects import *
+    else:
+        from .pipeline_visualcloze_combined import VisualClozePipeline
+        from .pipeline_visualcloze_generation import VisualClozeGenerationPipeline
+
+
+else:
+    import sys
+
+    sys.modules[__name__] = _LazyModule(
+        __name__,
+        globals()["__file__"],
+        _import_structure,
+        module_spec=__spec__,
+    )
+
+    for name, value in _dummy_objects.items():
+        setattr(sys.modules[__name__], name, value)