From 77a67b11c9d969689fa5ca02a67427328cd8b9f7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 17:58:53 -0700
Subject: [PATCH 01/21] Update pipeline_skyreels_v2_i2v.py

---
 .../pipelines/skyreels_v2/pipeline_skyreels_v2_i2v.py         | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_i2v.py b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_i2v.py
index d59b4ce3cb17..57adc5cc2ae7 100644
--- a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_i2v.py
+++ b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_i2v.py
@@ -524,9 +524,9 @@ def __call__(
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, defaults to `5.0`):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
+                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://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
+                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.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):

From ef10f5e43261b39a6835d9b8c5362bcf2b53fd3f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 18:04:46 -0700
Subject: [PATCH 02/21] Update README.md

---
 examples/community/README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/examples/community/README.md b/examples/community/README.md
index 4a4b0f5fd9f5..69e9c7576103 100644
--- a/examples/community/README.md
+++ b/examples/community/README.md
@@ -5488,7 +5488,7 @@ Editing at Scale", many thanks to their contribution!
 
 This implementation of Flux Kontext allows users to pass multiple reference images. Each image is encoded separately, and the resulting latent vectors are concatenated.
 
-As explained in Section 3 of [the paper](https://arxiv.org/pdf/2506.15742), the model's sequence concatenation mechanism can extend its capabilities to handle multiple reference images. However, note that the current version of Flux Kontext was not trained for this use case. In practice, stacking along the first axis does not yield correct results, while stacking along the other two axes appears to work.
+As explained in Section 3 of [the paper](https://huggingface.co/papers/2506.15742), the model's sequence concatenation mechanism can extend its capabilities to handle multiple reference images. However, note that the current version of Flux Kontext was not trained for this use case. In practice, stacking along the first axis does not yield correct results, while stacking along the other two axes appears to work.
 
 ## Example Usage
 

From 2b7fcc796ad9d482b9bafddf326fd0152ca9f0af Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 18:10:38 -0700
Subject: [PATCH 03/21] Update torch_utils.py

---
 src/diffusers/utils/torch_utils.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/diffusers/utils/torch_utils.py b/src/diffusers/utils/torch_utils.py
index a1ab8cda431f..13186723f179 100644
--- a/src/diffusers/utils/torch_utils.py
+++ b/src/diffusers/utils/torch_utils.py
@@ -243,7 +243,7 @@ def apply_freeu(
     resolution_idx: int, hidden_states: "torch.Tensor", res_hidden_states: "torch.Tensor", **freeu_kwargs
 ) -> Tuple["torch.Tensor", "torch.Tensor"]:
     """Applies the FreeU mechanism as introduced in https:
-    //arxiv.org/abs/2309.11497. Adapted from the official code repository: https://github.com/ChenyangSi/FreeU.
+    //huggingface.com/papers/2309.11497. Adapted from the official code repository: https://github.com/ChenyangSi/FreeU.
 
     Args:
         resolution_idx (`int`): Integer denoting the UNet block where FreeU is being applied.

From 29f829ca6f7843c5eab2916dab960732d49a88c2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 18:11:45 -0700
Subject: [PATCH 04/21] Update torch_utils.py

---
 src/diffusers/utils/torch_utils.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/diffusers/utils/torch_utils.py b/src/diffusers/utils/torch_utils.py
index 13186723f179..6642bb8aa8b3 100644
--- a/src/diffusers/utils/torch_utils.py
+++ b/src/diffusers/utils/torch_utils.py
@@ -243,7 +243,7 @@ def apply_freeu(
     resolution_idx: int, hidden_states: "torch.Tensor", res_hidden_states: "torch.Tensor", **freeu_kwargs
 ) -> Tuple["torch.Tensor", "torch.Tensor"]:
     """Applies the FreeU mechanism as introduced in https:
-    //huggingface.com/papers/2309.11497. Adapted from the official code repository: https://github.com/ChenyangSi/FreeU.
+    //huggingface.co/papers/2309.11497. Adapted from the official code repository: https://github.com/ChenyangSi/FreeU.
 
     Args:
         resolution_idx (`int`): Integer denoting the UNet block where FreeU is being applied.

From f0d47a2bae8d20c3e16baa718dea38f16531c8c9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 18:15:23 -0700
Subject: [PATCH 05/21] Update guider_utils.py

---
 src/diffusers/guiders/guider_utils.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/diffusers/guiders/guider_utils.py b/src/diffusers/guiders/guider_utils.py
index 71e4becfcdf3..3cd6f23ae49b 100644
--- a/src/diffusers/guiders/guider_utils.py
+++ b/src/diffusers/guiders/guider_utils.py
@@ -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`):

From 80bb767d89298c1d5464ff042deecba36be4c2c5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 18:20:36 -0700
Subject: [PATCH 06/21] Update pipeline_ltx.py

---
 src/diffusers/pipelines/ltx/pipeline_ltx.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/diffusers/pipelines/ltx/pipeline_ltx.py b/src/diffusers/pipelines/ltx/pipeline_ltx.py
index bd23e657c408..c9cd96d4b7a3 100644
--- a/src/diffusers/pipelines/ltx/pipeline_ltx.py
+++ b/src/diffusers/pipelines/ltx/pipeline_ltx.py
@@ -590,8 +590,8 @@ def __call__(
                 the text `prompt`, usually at the expense of lower image quality.
             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).
+                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.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of videos to generate per prompt.
@@ -777,7 +777,7 @@ def __call__(
                     noise_pred = noise_pred_uncond + self.guidance_scale * (noise_pred_text - noise_pred_uncond)
 
                     if self.guidance_rescale > 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
                         )

From 0314795f53f2b5cacf1d611f876f29c2f95e0c5b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 18:25:22 -0700
Subject: [PATCH 07/21] Update pipeline_bria.py

---
 src/diffusers/pipelines/bria/pipeline_bria.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/diffusers/pipelines/bria/pipeline_bria.py b/src/diffusers/pipelines/bria/pipeline_bria.py
index ebddfb0c0eee..03ed6c1b41fc 100644
--- a/src/diffusers/pipelines/bria/pipeline_bria.py
+++ b/src/diffusers/pipelines/bria/pipeline_bria.py
@@ -245,7 +245,7 @@ def guidance_scale(self):
         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):
@@ -489,9 +489,9 @@ def __call__(
                 in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                 passed will be used. Must be in descending order.
             guidance_scale (`float`, *optional*, defaults to 5.0):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
+                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://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
+                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*):

From c2c6aa5cb32e551012feba6fdba0c308aa9bcda4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 18:28:21 -0700
Subject: [PATCH 08/21] Apply suggestion from @qgallouedec

---
 src/diffusers/pipelines/bria/pipeline_bria.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/diffusers/pipelines/bria/pipeline_bria.py b/src/diffusers/pipelines/bria/pipeline_bria.py
index 03ed6c1b41fc..591879f720cd 100644
--- a/src/diffusers/pipelines/bria/pipeline_bria.py
+++ b/src/diffusers/pipelines/bria/pipeline_bria.py
@@ -491,7 +491,7 @@ def __call__(
             guidance_scale (`float`, *optional*, defaults to 5.0):
                 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 >
+                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*):

From 46105bdf36e8866bdaa6df47f561fa758838ae9e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 19:03:07 -0700
Subject: [PATCH 09/21] Update autoencoder_kl_qwenimage.py

---
 src/diffusers/models/autoencoders/autoencoder_kl_qwenimage.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/diffusers/models/autoencoders/autoencoder_kl_qwenimage.py b/src/diffusers/models/autoencoders/autoencoder_kl_qwenimage.py
index 14db6aeb61e3..5cba78464fa5 100644
--- a/src/diffusers/models/autoencoders/autoencoder_kl_qwenimage.py
+++ b/src/diffusers/models/autoencoders/autoencoder_kl_qwenimage.py
@@ -16,7 +16,7 @@
 # QwenImageVAE is further fine-tuned from the Wan Video VAE to achieve improved performance.
 # For more information about the Wan VAE, please refer to:
 # - GitHub: https://github.com/Wan-Video/Wan2.1
-# - arXiv: https://arxiv.org/abs/2503.20314
+# - Paper: https://huggingface.co/papers/2503.20314
 
 from typing import List, Optional, Tuple, Union
 

From 0fd611902513d3ce2d0480c392357abcc426f8de Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 19:05:51 -0700
Subject: [PATCH 10/21] Update pipeline_prx.py

---
 src/diffusers/pipelines/prx/pipeline_prx.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/diffusers/pipelines/prx/pipeline_prx.py b/src/diffusers/pipelines/prx/pipeline_prx.py
index a3bd3e6b45e7..a65ba760a751 100644
--- a/src/diffusers/pipelines/prx/pipeline_prx.py
+++ b/src/diffusers/pipelines/prx/pipeline_prx.py
@@ -536,9 +536,9 @@ def __call__(
                 in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                 passed will be used. Must be in descending order.
             guidance_scale (`float`, *optional*, defaults to 4.0):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
+                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://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
+                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.
             num_images_per_prompt (`int`, *optional*, defaults to 1):

From 2f32ab3df933dd4744782db9188a4e595370c2f5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 19:07:50 -0700
Subject: [PATCH 11/21] Update pipeline_wan_vace.py

---
 src/diffusers/pipelines/wan/pipeline_wan_vace.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/diffusers/pipelines/wan/pipeline_wan_vace.py b/src/diffusers/pipelines/wan/pipeline_wan_vace.py
index 63e557a98fbe..a7b4961a3098 100644
--- a/src/diffusers/pipelines/wan/pipeline_wan_vace.py
+++ b/src/diffusers/pipelines/wan/pipeline_wan_vace.py
@@ -758,9 +758,9 @@ def __call__(
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, defaults to `5.0`):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
+                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://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
+                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.
             guidance_scale_2 (`float`, *optional*, defaults to `None`):

From 7898b49e4721d5a0810873a2371c1cd6789b5531 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 20:30:02 -0700
Subject: [PATCH 12/21] Update pipeline_skyreels_v2.py

---
 src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2.py b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2.py
index 8562a5eaf0e6..9b746e14630d 100644
--- a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2.py
+++ b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2.py
@@ -415,9 +415,9 @@ def __call__(
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, defaults to `6.0`):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
+                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://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
+                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.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):

From 88464df9f91900072f298452a2ad3ce4fc87b74a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 20:31:07 -0700
Subject: [PATCH 13/21] Update pipeline_skyreels_v2_diffusion_forcing.py

---
 .../skyreels_v2/pipeline_skyreels_v2_diffusion_forcing.py     | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing.py b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing.py
index d0a4e118ce43..945a1105c540 100644
--- a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing.py
+++ b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing.py
@@ -647,9 +647,9 @@ def __call__(
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, defaults to `6.0`):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
+                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://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
+                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. (**6.0 for T2V**, **5.0 for I2V**)
             num_videos_per_prompt (`int`, *optional*, defaults to 1):

From 8df2ae0c9d34dd80667b03b967ec63de1de1a02e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 20:32:45 -0700
Subject: [PATCH 14/21] Update pipeline_bria_fibo.py

---
 src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo.py b/src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo.py
index 85d29029e667..2a222465767a 100644
--- a/src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo.py
+++ b/src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo.py
@@ -337,7 +337,7 @@ def guidance_scale(self):
         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
@@ -498,9 +498,9 @@ def __call__(
                 in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                 passed will be used. Must be in descending order.
             guidance_scale (`float`, *optional*, defaults to 5.0):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
+                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://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
+                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*):

From 69778222424a9c7796c2490b6100f83aef0b8378 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 20:34:31 -0700
Subject: [PATCH 15/21] Update pipeline_skyreels_v2_diffusion_forcing_i2v.py

---
 .../skyreels_v2/pipeline_skyreels_v2_diffusion_forcing_i2v.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing_i2v.py b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing_i2v.py
index 959cbb32f23a..526551001376 100644
--- a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing_i2v.py
+++ b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing_i2v.py
@@ -698,9 +698,9 @@ def __call__(
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, defaults to `5.0`):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
+                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://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
+                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. (**6.0 for T2V**, **5.0 for I2V**)
             num_videos_per_prompt (`int`, *optional*, defaults to 1):

From f17f7cb13c849ab7a28bbf304de8e25112201967 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 20:37:29 -0700
Subject: [PATCH 16/21] Update pipeline_ltx_condition.py

---
 src/diffusers/pipelines/ltx/pipeline_ltx_condition.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/diffusers/pipelines/ltx/pipeline_ltx_condition.py b/src/diffusers/pipelines/ltx/pipeline_ltx_condition.py
index 537588f67c95..7c0a46aa03c9 100644
--- a/src/diffusers/pipelines/ltx/pipeline_ltx_condition.py
+++ b/src/diffusers/pipelines/ltx/pipeline_ltx_condition.py
@@ -927,8 +927,8 @@ def __call__(
                 the text `prompt`, usually at the expense of lower image quality.
             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).
+                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.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of videos to generate per prompt.
@@ -1194,7 +1194,7 @@ def __call__(
                     timestep, _ = timestep.chunk(2)
 
                     if self.guidance_rescale > 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
                         )

From 73f84b2fce1bcc6de822ab11cf64042c07320282 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 20:39:10 -0700
Subject: [PATCH 17/21] Update pipeline_ltx_image2video.py

---
 src/diffusers/pipelines/ltx/pipeline_ltx_image2video.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/diffusers/pipelines/ltx/pipeline_ltx_image2video.py b/src/diffusers/pipelines/ltx/pipeline_ltx_image2video.py
index 694378b4f040..9e63a4cfc137 100644
--- a/src/diffusers/pipelines/ltx/pipeline_ltx_image2video.py
+++ b/src/diffusers/pipelines/ltx/pipeline_ltx_image2video.py
@@ -654,8 +654,8 @@ def __call__(
                 the text `prompt`, usually at the expense of lower image quality.
             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).
+                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.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of videos to generate per prompt.
@@ -851,7 +851,7 @@ def __call__(
                     timestep, _ = timestep.chunk(2)
 
                     if self.guidance_rescale > 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
                         )

From 3818edfa60b756a3f6bccf0e5244354ae7739d88 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?=
 <45557362+qgallouedec@users.noreply.github.com>
Date: Mon, 3 Nov 2025 20:44:30 -0700
Subject: [PATCH 18/21] Update regional_prompting_stable_diffusion.py

---
 .../community/regional_prompting_stable_diffusion.py   | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/examples/community/regional_prompting_stable_diffusion.py b/examples/community/regional_prompting_stable_diffusion.py
index bca67e3959d8..3bc780cfcf7a 100644
--- a/examples/community/regional_prompting_stable_diffusion.py
+++ b/examples/community/regional_prompting_stable_diffusion.py
@@ -490,7 +490,7 @@ def hook_forwards(root_module: torch.nn.Module):
     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())
@@ -841,7 +841,7 @@ def stable_diffusion_call(
             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
+                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
@@ -872,7 +872,7 @@ def stable_diffusion_call(
                 [`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
@@ -1062,7 +1062,7 @@ def stable_diffusion_call(
                     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)
 
                 # compute the previous noisy sample x_t -> x_t-1
@@ -1668,7 +1668,7 @@ 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`):

From 847c195709f2afd9e76110fb07cc94897d693941 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?= <gallouedec.quentin@gmail.com>
Date: Tue, 4 Nov 2025 03:59:05 +0000
Subject: [PATCH 19/21] make style

---
 src/diffusers/pipelines/bria/pipeline_bria.py          | 10 +++++-----
 .../pipelines/bria_fibo/pipeline_bria_fibo.py          | 10 +++++-----
 src/diffusers/pipelines/ltx/pipeline_ltx.py            |  5 +++--
 src/diffusers/pipelines/ltx/pipeline_ltx_condition.py  |  5 +++--
 .../pipelines/ltx/pipeline_ltx_image2video.py          |  5 +++--
 src/diffusers/pipelines/prx/pipeline_prx.py            | 10 +++++-----
 .../pipelines/skyreels_v2/pipeline_skyreels_v2.py      | 10 +++++-----
 .../pipeline_skyreels_v2_diffusion_forcing.py          | 10 +++++-----
 .../pipeline_skyreels_v2_diffusion_forcing_i2v.py      | 10 +++++-----
 .../pipelines/skyreels_v2/pipeline_skyreels_v2_i2v.py  | 10 +++++-----
 src/diffusers/pipelines/wan/pipeline_wan_vace.py       | 10 +++++-----
 11 files changed, 49 insertions(+), 46 deletions(-)

diff --git a/src/diffusers/pipelines/bria/pipeline_bria.py b/src/diffusers/pipelines/bria/pipeline_bria.py
index 591879f720cd..a22a756005ac 100644
--- a/src/diffusers/pipelines/bria/pipeline_bria.py
+++ b/src/diffusers/pipelines/bria/pipeline_bria.py
@@ -489,11 +489,11 @@ def __call__(
                 in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                 passed will be used. Must be in descending order.
             guidance_scale (`float`, *optional*, defaults to 5.0):
-                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.
+                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
diff --git a/src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo.py b/src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo.py
index 2a222465767a..c66b64766edc 100644
--- a/src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo.py
+++ b/src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo.py
@@ -498,11 +498,11 @@ def __call__(
                 in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                 passed will be used. Must be in descending order.
             guidance_scale (`float`, *optional*, defaults to 5.0):
-                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.
+                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
diff --git a/src/diffusers/pipelines/ltx/pipeline_ltx.py b/src/diffusers/pipelines/ltx/pipeline_ltx.py
index c9cd96d4b7a3..8ca8b4419e18 100644
--- a/src/diffusers/pipelines/ltx/pipeline_ltx.py
+++ b/src/diffusers/pipelines/ltx/pipeline_ltx.py
@@ -591,8 +591,9 @@ def __call__(
             guidance_rescale (`float`, *optional*, defaults to 0.0):
                 Guidance rescale factor proposed by [Common Diffusion Noise Schedules and Sample Steps are
                 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.
+                [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.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of videos to generate per prompt.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
diff --git a/src/diffusers/pipelines/ltx/pipeline_ltx_condition.py b/src/diffusers/pipelines/ltx/pipeline_ltx_condition.py
index 7c0a46aa03c9..48a6f0837c8d 100644
--- a/src/diffusers/pipelines/ltx/pipeline_ltx_condition.py
+++ b/src/diffusers/pipelines/ltx/pipeline_ltx_condition.py
@@ -928,8 +928,9 @@ def __call__(
             guidance_rescale (`float`, *optional*, defaults to 0.0):
                 Guidance rescale factor proposed by [Common Diffusion Noise Schedules and Sample Steps are
                 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.
+                [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.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of videos to generate per prompt.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
diff --git a/src/diffusers/pipelines/ltx/pipeline_ltx_image2video.py b/src/diffusers/pipelines/ltx/pipeline_ltx_image2video.py
index 9e63a4cfc137..f30f8a3dc8f6 100644
--- a/src/diffusers/pipelines/ltx/pipeline_ltx_image2video.py
+++ b/src/diffusers/pipelines/ltx/pipeline_ltx_image2video.py
@@ -655,8 +655,9 @@ def __call__(
             guidance_rescale (`float`, *optional*, defaults to 0.0):
                 Guidance rescale factor proposed by [Common Diffusion Noise Schedules and Sample Steps are
                 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.
+                [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.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of videos to generate per prompt.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
diff --git a/src/diffusers/pipelines/prx/pipeline_prx.py b/src/diffusers/pipelines/prx/pipeline_prx.py
index a65ba760a751..df598a5715d2 100644
--- a/src/diffusers/pipelines/prx/pipeline_prx.py
+++ b/src/diffusers/pipelines/prx/pipeline_prx.py
@@ -536,11 +536,11 @@ def __call__(
                 in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                 passed will be used. Must be in descending order.
             guidance_scale (`float`, *optional*, defaults to 4.0):
-                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.
+                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.
             num_images_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
diff --git a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2.py b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2.py
index 9b746e14630d..d6cd7d7feceb 100644
--- a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2.py
+++ b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2.py
@@ -415,11 +415,11 @@ def __call__(
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, defaults to `6.0`):
-                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.
+                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.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
diff --git a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing.py b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing.py
index 945a1105c540..089f92632d38 100644
--- a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing.py
+++ b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing.py
@@ -647,11 +647,11 @@ def __call__(
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, defaults to `6.0`):
-                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. (**6.0 for T2V**, **5.0 for I2V**)
+                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. (**6.0 for T2V**, **5.0 for I2V**)
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
diff --git a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing_i2v.py b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing_i2v.py
index 526551001376..2951a9447386 100644
--- a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing_i2v.py
+++ b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_diffusion_forcing_i2v.py
@@ -698,11 +698,11 @@ def __call__(
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, defaults to `5.0`):
-                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. (**6.0 for T2V**, **5.0 for I2V**)
+                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. (**6.0 for T2V**, **5.0 for I2V**)
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
diff --git a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_i2v.py b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_i2v.py
index 57adc5cc2ae7..d61b687eadc3 100644
--- a/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_i2v.py
+++ b/src/diffusers/pipelines/skyreels_v2/pipeline_skyreels_v2_i2v.py
@@ -524,11 +524,11 @@ def __call__(
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, defaults to `5.0`):
-                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.
+                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.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
diff --git a/src/diffusers/pipelines/wan/pipeline_wan_vace.py b/src/diffusers/pipelines/wan/pipeline_wan_vace.py
index a7b4961a3098..351ae2e70563 100644
--- a/src/diffusers/pipelines/wan/pipeline_wan_vace.py
+++ b/src/diffusers/pipelines/wan/pipeline_wan_vace.py
@@ -758,11 +758,11 @@ def __call__(
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, defaults to `5.0`):
-                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.
+                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.
             guidance_scale_2 (`float`, *optional*, defaults to `None`):
                 Guidance scale for the low-noise stage transformer (`transformer_2`). If `None` and the pipeline's
                 `boundary_ratio` is not None, uses the same value as `guidance_scale`. Only used when `transformer_2`

From 5bd71e26a765d8925db782ed8752745038038d59 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?= <gallouedec.quentin@gmail.com>
Date: Tue, 4 Nov 2025 04:02:50 +0000
Subject: [PATCH 20/21] style

---
 src/diffusers/utils/torch_utils.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/diffusers/utils/torch_utils.py b/src/diffusers/utils/torch_utils.py
index 6642bb8aa8b3..d6ca5f26ad02 100644
--- a/src/diffusers/utils/torch_utils.py
+++ b/src/diffusers/utils/torch_utils.py
@@ -242,8 +242,8 @@ def fourier_filter(x_in: "torch.Tensor", threshold: int, scale: int) -> "torch.T
 def apply_freeu(
     resolution_idx: int, hidden_states: "torch.Tensor", res_hidden_states: "torch.Tensor", **freeu_kwargs
 ) -> Tuple["torch.Tensor", "torch.Tensor"]:
-    """Applies the FreeU mechanism as introduced in https:
-    //huggingface.co/papers/2309.11497. Adapted from the official code repository: https://github.com/ChenyangSi/FreeU.
+    """Applies the FreeU mechanism as introduced in https://huggingface.co/papers/2309.11497. Adapted from the official
+    code repository: https://github.com/ChenyangSi/FreeU.
 
     Args:
         resolution_idx (`int`): Integer denoting the UNet block where FreeU is being applied.

From cc8c328878b7c040f55c55dc6c1ba51aaeba8472 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20Gallou=C3=A9dec?= <gallouedec.quentin@gmail.com>
Date: Tue, 4 Nov 2025 04:04:53 +0000
Subject: [PATCH 21/21] style

---
 docs/source/en/_toctree.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/source/en/_toctree.yml b/docs/source/en/_toctree.yml
index 251eb25899ce..5af95cba7490 100644
--- a/docs/source/en/_toctree.yml
+++ b/docs/source/en/_toctree.yml
@@ -636,6 +636,8 @@
         title: HunyuanVideo
       - local: api/pipelines/i2vgenxl
         title: I2VGen-XL
+      - local: api/pipelines/kandinsky5_video
+        title: Kandinsky 5.0 Video
       - local: api/pipelines/latte
         title: Latte
       - local: api/pipelines/ltx_video
@@ -654,8 +656,6 @@
         title: Text2Video-Zero
       - local: api/pipelines/wan
         title: Wan
-      - local: api/pipelines/kandinsky5_video
-        title: Kandinsky 5.0 Video
       title: Video
     title: Pipelines
   - sections: