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

diffusers/pipelines/kandinsky3/pipeline_kandinsky3_img2img.py

@@ -1,12 +1,12 @@
 import inspect
 from typing import Callable, Dict, List, Optional, Union
 
-import numpy as np
 import PIL
 import PIL.Image
 import torch
 from transformers import T5EncoderModel, T5Tokenizer
 
+from ...image_processor import VaeImageProcessor
 from ...loaders import StableDiffusionLoraLoaderMixin
 from ...models import Kandinsky3UNet, VQModel
 from ...schedulers import DDPMScheduler
@@ -53,24 +53,6 @@ EXAMPLE_DOC_STRING = """
 """
 
 
-def downscale_height_and_width(height, width, scale_factor=8):
-    new_height = height // scale_factor**2
-    if height % scale_factor**2 != 0:
-        new_height += 1
-    new_width = width // scale_factor**2
-    if width % scale_factor**2 != 0:
-        new_width += 1
-    return new_height * scale_factor, new_width * scale_factor
-
-
-def prepare_image(pil_image):
-    arr = np.array(pil_image.convert("RGB"))
-    arr = arr.astype(np.float32) / 127.5 - 1
-    arr = np.transpose(arr, [2, 0, 1])
-    image = torch.from_numpy(arr).unsqueeze(0)
-    return image
-
-
 class Kandinsky3Img2ImgPipeline(DiffusionPipeline, StableDiffusionLoraLoaderMixin):
     model_cpu_offload_seq = "text_encoder->movq->unet->movq"
     _callback_tensor_inputs = [
@@ -94,6 +76,14 @@ class Kandinsky3Img2ImgPipeline(DiffusionPipeline, StableDiffusionLoraLoaderMixi
         self.register_modules(
             tokenizer=tokenizer, text_encoder=text_encoder, unet=unet, scheduler=scheduler, movq=movq
         )
+        movq_scale_factor = 2 ** (len(self.movq.config.block_out_channels) - 1) if getattr(self, "movq", None) else 8
+        movq_latent_channels = self.movq.config.latent_channels if getattr(self, "movq", None) else 4
+        self.image_processor = VaeImageProcessor(
+            vae_scale_factor=movq_scale_factor,
+            vae_latent_channels=movq_latent_channels,
+            resample="bicubic",
+            reducing_gap=1,
+        )
 
     def get_timesteps(self, num_inference_steps, strength, device):
         # get the original timestep using init_timestep
@@ -309,7 +299,7 @@ class Kandinsky3Img2ImgPipeline(DiffusionPipeline, StableDiffusionLoraLoaderMixi
     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())
@@ -449,11 +439,11 @@ class Kandinsky3Img2ImgPipeline(DiffusionPipeline, StableDiffusionLoraLoaderMixi
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, *optional*, defaults to 3.0):
-                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 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
@@ -566,7 +556,7 @@ class Kandinsky3Img2ImgPipeline(DiffusionPipeline, StableDiffusionLoraLoaderMixi
                 f"Input is in incorrect format: {[type(i) for i in image]}. Currently, we only support  PIL image and pytorch tensor"
             )
 
-        image = torch.cat([prepare_image(i) for i in image], dim=0)
+        image = torch.cat([self.image_processor.preprocess(i) for i in image], dim=0)
         image = image.to(dtype=prompt_embeds.dtype, device=device)
         # 4. Prepare timesteps
         self.scheduler.set_timesteps(num_inference_steps, device=device)
@@ -630,20 +620,9 @@ class Kandinsky3Img2ImgPipeline(DiffusionPipeline, StableDiffusionLoraLoaderMixi
                     xm.mark_step()
 
             # post-processing
-            if output_type not in ["pt", "np", "pil", "latent"]:
-                raise ValueError(
-                    f"Only the output types `pt`, `pil`, `np` and `latent` are supported not output_type={output_type}"
-                )
             if not output_type == "latent":
                 image = self.movq.decode(latents, force_not_quantize=True)["sample"]
-
-                if output_type in ["np", "pil"]:
-                    image = image * 0.5 + 0.5
-                    image = image.clamp(0, 1)
-                    image = image.cpu().permute(0, 2, 3, 1).float().numpy()
-
-                if output_type == "pil":
-                    image = self.numpy_to_pil(image)
+                image = self.image_processor.postprocess(image, output_type)
             else:
                 image = latents
 

diffusers/pipelines/kolors/pipeline_kolors.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Stability AI, Kwai-Kolors Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Stability AI, Kwai-Kolors Team 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.
@@ -436,7 +436,7 @@ class KolorsPipeline(DiffusionPipeline, StableDiffusionMixin, StableDiffusionLor
     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())
@@ -633,7 +633,7 @@ class KolorsPipeline(DiffusionPipeline, StableDiffusionMixin, StableDiffusionLor
         return self._guidance_scale
 
     # 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):
@@ -729,11 +729,11 @@ class KolorsPipeline(DiffusionPipeline, StableDiffusionMixin, StableDiffusionLor
                 "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 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
@@ -741,8 +741,8 @@ class KolorsPipeline(DiffusionPipeline, StableDiffusionMixin, StableDiffusionLor
             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) 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.

diffusers/pipelines/kolors/pipeline_kolors_img2img.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Stability AI, Kwai-Kolors Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Stability AI, Kwai-Kolors Team 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.
@@ -25,7 +25,7 @@ from ...models import AutoencoderKL, ImageProjection, UNet2DConditionModel
 from ...models.attention_processor import AttnProcessor2_0, FusedAttnProcessor2_0, XFormersAttnProcessor
 from ...schedulers import KarrasDiffusionSchedulers
 from ...utils import is_torch_xla_available, logging, replace_example_docstring
-from ...utils.torch_utils import randn_tensor
+from ...utils.torch_utils import empty_device_cache, randn_tensor
 from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from .pipeline_output import KolorsPipelineOutput
 from .text_encoder import ChatGLMModel
@@ -456,7 +456,7 @@ class KolorsImg2ImgPipeline(DiffusionPipeline, StableDiffusionMixin, StableDiffu
     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())
@@ -618,7 +618,7 @@ class KolorsImg2ImgPipeline(DiffusionPipeline, StableDiffusionMixin, StableDiffu
         # Offload text encoder if `enable_model_cpu_offload` was enabled
         if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None:
             self.text_encoder_2.to("cpu")
-            torch.cuda.empty_cache()
+            empty_device_cache()
 
         image = image.to(device=device, dtype=dtype)
 
@@ -761,7 +761,7 @@ class KolorsImg2ImgPipeline(DiffusionPipeline, StableDiffusionMixin, StableDiffu
         return self._guidance_scale
 
     # 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):
@@ -880,11 +880,11 @@ class KolorsImg2ImgPipeline(DiffusionPipeline, StableDiffusionMixin, StableDiffu
                 "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 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
@@ -892,8 +892,8 @@ class KolorsImg2ImgPipeline(DiffusionPipeline, StableDiffusionMixin, StableDiffu
             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) 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.

diffusers/pipelines/kolors/text_encoder.py

@@ -1,4 +1,4 @@
-# Copyright 2024 ChatGLM3-6B Model Team, Kwai-Kolors Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 ChatGLM3-6B Model Team, Kwai-Kolors Team 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.
@@ -434,7 +434,7 @@ class MLP(torch.nn.Module):
 
         self.add_bias = config.add_bias_linear
 
-        # Project to 4h. If using swiglu double the output width, see https://arxiv.org/pdf/2002.05202.pdf
+        # Project to 4h. If using swiglu double the output width, see https://huggingface.co/papers/2002.05202
         self.dense_h_to_4h = nn.Linear(
             config.hidden_size,
             config.ffn_hidden_size * 2,
@@ -668,7 +668,7 @@ class Embedding(torch.nn.Module):
         # Embeddings.
         words_embeddings = self.word_embeddings(input_ids)
         embeddings = words_embeddings
-        # Data format change to avoid explicit tranposes : [b s h] --> [s b h].
+        # Data format change to avoid explicit transposes : [b s h] --> [s b h].
         embeddings = embeddings.transpose(0, 1).contiguous()
         # If the input flag for fp32 residual connection is set, convert for float.
         if self.fp32_residual_connection:

diffusers/pipelines/kolors/tokenizer.py

@@ -1,4 +1,4 @@
-# Copyright 2024 ChatGLM3-6B Model Team, Kwai-Kolors Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 ChatGLM3-6B Model Team, Kwai-Kolors Team 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.

diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_img2img.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Stanford University Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Stanford University Team 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.
@@ -607,7 +607,7 @@ class LatentConsistencyModelImg2ImgPipeline(
     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/latent_consistency_models/pipeline_latent_consistency_text2img.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Stanford University Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Stanford University Team 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.
@@ -548,7 +548,7 @@ class LatentConsistencyModelPipeline(
     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/latent_diffusion/pipeline_latent_diffusion.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.

diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion_superresolution.py

@@ -95,8 +95,8 @@ class LDMSuperResolutionPipeline(DiffusionPipeline):
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             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.
@@ -166,7 +166,7 @@ class LDMSuperResolutionPipeline(DiffusionPipeline):
 
         # 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())
         extra_kwargs = {}

diffusers/pipelines/latte/pipeline_latte.py

@@ -1,4 +1,4 @@
-# Copyright 2024 the Latte Team and The HuggingFace Team.
+# Copyright 2025 the Latte Team and The HuggingFace Team.
 # All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -356,7 +356,7 @@ class LattePipeline(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())
@@ -501,7 +501,7 @@ class LattePipeline(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:
@@ -592,7 +592,7 @@ class LattePipeline(DiffusionPipeline):
         return self._guidance_scale
 
     # 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):
@@ -657,11 +657,11 @@ class LattePipeline(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 7.0):
-                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 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.
             video_length (`int`, *optional*, defaults to 16):
                 The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds
             num_images_per_prompt (`int`, *optional*, defaults to 1):
@@ -671,8 +671,8 @@ class LattePipeline(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.
@@ -747,7 +747,7 @@ class LattePipeline(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/ledits_pp/pipeline_leditspp_stable_diffusion.py

@@ -244,7 +244,7 @@ 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`):
@@ -439,7 +439,7 @@ class LEditsPPPipelineStableDiffusion(
     def prepare_extra_step_kwargs(self, eta, generator=None):
         # 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())
@@ -808,7 +808,7 @@ class LEditsPPPipelineStableDiffusion(
             edit_guidance_scale (`float` or `List[float]`, *optional*, defaults to 5):
                 Guidance scale for guiding the image generation. If provided as list values should correspond to
                 `editing_prompt`. `edit_guidance_scale` is defined as `s_e` of equation 12 of [LEDITS++
-                Paper](https://arxiv.org/abs/2301.12247).
+                Paper](https://huggingface.co/papers/2301.12247).
             edit_warmup_steps (`float` or `List[float]`, *optional*, defaults to 10):
                 Number of diffusion steps (for each prompt) for which guidance will not be applied.
             edit_cooldown_steps (`float` or `List[float]`, *optional*, defaults to `None`):
@@ -816,7 +816,7 @@ class LEditsPPPipelineStableDiffusion(
             edit_threshold (`float` or `List[float]`, *optional*, defaults to 0.9):
                 Masking threshold of guidance. Threshold should be proportional to the image region that is modified.
                 'edit_threshold' is defined as 'λ' of equation 12 of [LEDITS++
-                Paper](https://arxiv.org/abs/2301.12247).
+                Paper](https://huggingface.co/papers/2301.12247).
             user_mask (`torch.Tensor`, *optional*):
                 User-provided mask for even better control over the editing process. This is helpful when LEDITS++'s
                 implicit masks do not meet user preferences.
@@ -826,11 +826,11 @@ class LEditsPPPipelineStableDiffusion(
             use_cross_attn_mask (`bool`, defaults to `False`):
                 Whether cross-attention masks are used. Cross-attention masks are always used when use_intersect_mask
                 is set to true. Cross-attention masks are defined as 'M^1' of equation 12 of [LEDITS++
-                paper](https://arxiv.org/pdf/2311.16711.pdf).
+                paper](https://huggingface.co/papers/2311.16711).
             use_intersect_mask (`bool`, defaults to `True`):
                 Whether the masking term is calculated as intersection of cross-attention masks and masks derived from
                 the noise estimate. Cross-attention mask are defined as 'M^1' and masks derived from the noise estimate
-                are defined as 'M^2' of equation 12 of [LEDITS++ paper](https://arxiv.org/pdf/2311.16711.pdf).
+                are defined as 'M^2' of equation 12 of [LEDITS++ paper](https://huggingface.co/papers/2311.16711).
             attn_store_steps (`List[int]`, *optional*):
                 Steps for which the attention maps are stored in the AttentionStore. Just for visualization purposes.
             store_averaged_over_steps (`bool`, defaults to `True`):
@@ -841,7 +841,7 @@ class LEditsPPPipelineStableDiffusion(
                 [`self.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 from [Common Diffusion Noise Schedules and Sample Steps are
-                Flawed](https://arxiv.org/pdf/2305.08891.pdf). Guidance rescale factor should fix overexposure when
+                Flawed](https://huggingface.co/papers/2305.08891). Guidance rescale factor should fix overexposure when
                 using zero terminal SNR.
             clip_skip (`int`, *optional*):
                 Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
@@ -1191,7 +1191,7 @@ class LEditsPPPipelineStableDiffusion(
                 noise_pred = noise_pred_uncond + noise_guidance_edit
 
                 if enable_edit_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_edit_concepts.mean(dim=0, keepdim=False),
@@ -1268,8 +1268,8 @@ class LEditsPPPipelineStableDiffusion(
     ):
         r"""
         The function to the pipeline for image inversion as described by the [LEDITS++
-        Paper](https://arxiv.org/abs/2301.12247). If the scheduler is set to [`~schedulers.DDIMScheduler`] the
-        inversion proposed by [edit-friendly DPDM](https://arxiv.org/abs/2304.06140) will be performed instead.
+        Paper](https://huggingface.co/papers/2301.12247). If the scheduler is set to [`~schedulers.DDIMScheduler`] the
+        inversion proposed by [edit-friendly DPDM](https://huggingface.co/papers/2304.06140) will be performed instead.
 
         Args:
             image (`PipelineImageInput`):
@@ -1443,7 +1443,7 @@ def compute_noise_ddim(scheduler, prev_latents, latents, timestep, noise_pred, e
     beta_prod_t = 1 - alpha_prod_t
 
     # 3. compute predicted original sample from predicted noise also called
-    # "predicted x_0" of formula (12) from https://arxiv.org/pdf/2010.02502.pdf
+    # "predicted x_0" of formula (12) from https://huggingface.co/papers/2010.02502
     pred_original_sample = (latents - beta_prod_t ** (0.5) * noise_pred) / alpha_prod_t ** (0.5)
 
     # 4. Clip "predicted x_0"
@@ -1455,10 +1455,10 @@ def compute_noise_ddim(scheduler, prev_latents, latents, timestep, noise_pred, e
     variance = scheduler._get_variance(timestep, prev_timestep)
     std_dev_t = eta * variance ** (0.5)
 
-    # 6. compute "direction pointing to x_t" of formula (12) from https://arxiv.org/pdf/2010.02502.pdf
+    # 6. compute "direction pointing to x_t" of formula (12) from https://huggingface.co/papers/2010.02502
     pred_sample_direction = (1 - alpha_prod_t_prev - std_dev_t**2) ** (0.5) * noise_pred
 
-    # modifed so that updated xtm1 is returned as well (to avoid error accumulation)
+    # modified so that updated xtm1 is returned as well (to avoid error accumulation)
     mu_xt = alpha_prod_t_prev ** (0.5) * pred_original_sample + pred_sample_direction
     if variance > 0.0:
         noise = (prev_latents - mu_xt) / (variance ** (0.5) * eta)

diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion_xl.py

@@ -622,7 +622,7 @@ class LEditsPPPipelineStableDiffusionXL(
     def prepare_extra_step_kwargs(self, eta, generator=None):
         # 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())
@@ -747,7 +747,7 @@ class LEditsPPPipelineStableDiffusionXL(
         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):
@@ -901,9 +901,10 @@ class LEditsPPPipelineStableDiffusionXL(
                 [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.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.
             crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
                 `crops_coords_top_left` can be used to generate an image that appears to be "cropped" from the position
                 `crops_coords_top_left` downwards. Favorable, well-centered images are usually achieved by setting
@@ -929,7 +930,7 @@ class LEditsPPPipelineStableDiffusionXL(
             edit_guidance_scale (`float` or `List[float]`, *optional*, defaults to 5):
                 Guidance scale for guiding the image generation. If provided as list values should correspond to
                 `editing_prompt`. `edit_guidance_scale` is defined as `s_e` of equation 12 of [LEDITS++
-                Paper](https://arxiv.org/abs/2301.12247).
+                Paper](https://huggingface.co/papers/2301.12247).
             edit_warmup_steps (`float` or `List[float]`, *optional*, defaults to 10):
                 Number of diffusion steps (for each prompt) for which guidance is not applied.
             edit_cooldown_steps (`float` or `List[float]`, *optional*, defaults to `None`):
@@ -937,18 +938,18 @@ class LEditsPPPipelineStableDiffusionXL(
             edit_threshold (`float` or `List[float]`, *optional*, defaults to 0.9):
                 Masking threshold of guidance. Threshold should be proportional to the image region that is modified.
                 'edit_threshold' is defined as 'λ' of equation 12 of [LEDITS++
-                Paper](https://arxiv.org/abs/2301.12247).
+                Paper](https://huggingface.co/papers/2301.12247).
             sem_guidance (`List[torch.Tensor]`, *optional*):
                 List of pre-generated guidance vectors to be applied at generation. Length of the list has to
                 correspond to `num_inference_steps`.
             use_cross_attn_mask:
                 Whether cross-attention masks are used. Cross-attention masks are always used when use_intersect_mask
                 is set to true. Cross-attention masks are defined as 'M^1' of equation 12 of [LEDITS++
-                paper](https://arxiv.org/pdf/2311.16711.pdf).
+                paper](https://huggingface.co/papers/2311.16711).
             use_intersect_mask:
                 Whether the masking term is calculated as intersection of cross-attention masks and masks derived from
                 the noise estimate. Cross-attention mask are defined as 'M^1' and masks derived from the noise estimate
-                are defined as 'M^2' of equation 12 of [LEDITS++ paper](https://arxiv.org/pdf/2311.16711.pdf).
+                are defined as 'M^2' of equation 12 of [LEDITS++ paper](https://huggingface.co/papers/2311.16711).
             user_mask:
                 User-provided mask for even better control over the editing process. This is helpful when LEDITS++'s
                 implicit masks do not meet user preferences.
@@ -1350,7 +1351,7 @@ class LEditsPPPipelineStableDiffusionXL(
 
                 # compute the previous noisy sample x_t -> x_t-1
                 if enable_edit_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_edit_concepts.mean(dim=0, keepdim=False),
@@ -1478,8 +1479,8 @@ class LEditsPPPipelineStableDiffusionXL(
     ):
         r"""
         The function to the pipeline for image inversion as described by the [LEDITS++
-        Paper](https://arxiv.org/abs/2301.12247). If the scheduler is set to [`~schedulers.DDIMScheduler`] the
-        inversion proposed by [edit-friendly DPDM](https://arxiv.org/abs/2304.06140) will be performed instead.
+        Paper](https://huggingface.co/papers/2301.12247). If the scheduler is set to [`~schedulers.DDIMScheduler`] the
+        inversion proposed by [edit-friendly DPDM](https://huggingface.co/papers/2304.06140) will be performed instead.
 
         Args:
             image (`PipelineImageInput`):
@@ -1691,7 +1692,7 @@ 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`):
@@ -1727,7 +1728,7 @@ def compute_noise_ddim(scheduler, prev_latents, latents, timestep, noise_pred, e
     beta_prod_t = 1 - alpha_prod_t
 
     # 3. compute predicted original sample from predicted noise also called
-    # "predicted x_0" of formula (12) from https://arxiv.org/pdf/2010.02502.pdf
+    # "predicted x_0" of formula (12) from https://huggingface.co/papers/2010.02502
     pred_original_sample = (latents - beta_prod_t ** (0.5) * noise_pred) / alpha_prod_t ** (0.5)
 
     # 4. Clip "predicted x_0"
@@ -1739,10 +1740,10 @@ def compute_noise_ddim(scheduler, prev_latents, latents, timestep, noise_pred, e
     variance = scheduler._get_variance(timestep, prev_timestep)
     std_dev_t = eta * variance ** (0.5)
 
-    # 6. compute "direction pointing to x_t" of formula (12) from https://arxiv.org/pdf/2010.02502.pdf
+    # 6. compute "direction pointing to x_t" of formula (12) from https://huggingface.co/papers/2010.02502
     pred_sample_direction = (1 - alpha_prod_t_prev - std_dev_t**2) ** (0.5) * noise_pred
 
-    # modifed so that updated xtm1 is returned as well (to avoid error accumulation)
+    # modified so that updated xtm1 is returned as well (to avoid error accumulation)
     mu_xt = alpha_prod_t_prev ** (0.5) * pred_original_sample + pred_sample_direction
     if variance > 0.0:
         noise = (prev_latents - mu_xt) / (variance ** (0.5) * eta)