ArXiv -> HF Papers

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
 

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`):

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*):

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
                         )

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):

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.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.