Use HF Papers (#11567)

* Use HF Papers

* Apply style fixes

---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

examples/community/stable_diffusion_reference.py

@@ -655,7 +655,7 @@ class StableDiffusionReferencePipeline(
         """
         # 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())
@@ -865,9 +865,9 @@ class StableDiffusionReferencePipeline(
                 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 7.5):
-                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*):
@@ -877,7 +877,7 @@ class StableDiffusionReferencePipeline(
             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
+                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)
@@ -911,8 +911,8 @@ class StableDiffusionReferencePipeline(
                 [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
             guidance_rescale (`float`, *optional*, defaults to 0.0):
                 Guidance rescale factor proposed by [Common Diffusion Noise Schedules and Sample Steps are
-                Flawed](https://arxiv.org/pdf/2305.08891.pdf) `guidance_scale` is defined as `φ` in equation 16. of
-                [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf).
+                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.
             attention_auto_machine_weight (`float`):
                 Weight of using reference query for self attention's context.
@@ -956,7 +956,7 @@ class StableDiffusionReferencePipeline(
 
         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
 
@@ -1432,7 +1432,7 @@ class StableDiffusionReferencePipeline(
                     noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
 
                 if do_classifier_free_guidance and guidance_rescale > 0.0:
-                    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
+                    # Based on 3.4. in https://huggingface.co/papers/2305.08891
                     noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=guidance_rescale)
 
                 # compute the previous noisy sample x_t -> x_t-1

examples/community/stable_diffusion_repaint.py

@@ -442,7 +442,7 @@ class StableDiffusionRepaintPipeline(
     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())
@@ -653,14 +653,14 @@ class StableDiffusionRepaintPipeline(
                 expense of slower inference.
             jump_length (`int`, *optional*, defaults to 10):
                 The number of steps taken forward in time before going backward in time for a single jump ("j" in
-                RePaint paper). Take a look at Figure 9 and 10 in https://arxiv.org/pdf/2201.09865.pdf.
+                RePaint paper). Take a look at Figure 9 and 10 in https://huggingface.co/papers/2201.09865.
             jump_n_sample (`int`, *optional*, defaults to 10):
                 The number of times we will make forward time jump for a given chosen time sample. Take a look at
-                Figure 9 and 10 in https://arxiv.org/pdf/2201.09865.pdf.
+                Figure 9 and 10 in https://huggingface.co/papers/2201.09865.
             guidance_scale (`float`, *optional*, defaults to 7.5):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
+                Guidance scale 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*):
@@ -670,7 +670,7 @@ class StableDiffusionRepaintPipeline(
             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
+                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`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
@@ -759,7 +759,7 @@ class StableDiffusionRepaintPipeline(
 
         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
 

examples/community/stable_diffusion_tensorrt_img2img.py

@@ -1059,9 +1059,9 @@ class TensorRTStableDiffusionImg2ImgPipeline(DiffusionPipeline):
                 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 7.5):
-                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*):

examples/community/stable_diffusion_tensorrt_inpaint.py

@@ -1148,9 +1148,9 @@ class TensorRTStableDiffusionInpaintPipeline(DiffusionPipeline):
                 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 7.5):
-                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*):

examples/community/stable_diffusion_tensorrt_txt2img.py

@@ -982,9 +982,9 @@ class TensorRTStableDiffusionPipeline(DiffusionPipeline):
                 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 7.5):
-                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*):

examples/community/stable_diffusion_xl_controlnet_reference.py

@@ -431,7 +431,7 @@ class StableDiffusionXLControlNetReferencePipeline(StableDiffusionXLControlNetPi
             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

examples/community/stable_diffusion_xl_reference.py

@@ -65,7 +65,7 @@ def torch_dfs(model: torch.nn.Module):
 def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
     """
     Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and
-    Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf). See Section 3.4
+    Sample Steps are Flawed](https://huggingface.co/papers/2305.08891). See Section 3.4
     """
     std_text = noise_pred_text.std(dim=list(range(1, noise_pred_text.ndim)), keepdim=True)
     std_cfg = noise_cfg.std(dim=list(range(1, noise_cfg.ndim)), keepdim=True)
@@ -357,9 +357,9 @@ class StableDiffusionXLReferencePipeline(StableDiffusionXLPipeline):
                 "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 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*):
@@ -372,7 +372,7 @@ class StableDiffusionXLReferencePipeline(StableDiffusionXLPipeline):
             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
+                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)
@@ -413,8 +413,8 @@ class StableDiffusionXLReferencePipeline(StableDiffusionXLPipeline):
                 [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
             guidance_rescale (`float`, *optional*, defaults to 0.0):
                 Guidance rescale factor proposed by [Common Diffusion Noise Schedules and Sample Steps are
-                Flawed](https://arxiv.org/pdf/2305.08891.pdf) `guidance_scale` is defined as `φ` in equation 16. of
-                [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf).
+                Flawed](https://huggingface.co/papers/2305.08891) `guidance_scale` is defined as `φ` in equation 16. of
+                [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://huggingface.co/papers/2305.08891).
                 Guidance rescale factor should fix overexposure when using zero terminal SNR.
             original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                 If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
@@ -1114,7 +1114,7 @@ class StableDiffusionXLReferencePipeline(StableDiffusionXLPipeline):
                     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

examples/community/text_inpainting.py

@@ -161,9 +161,9 @@ class TextInpainting(DiffusionPipeline, StableDiffusionMixin):
                 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 7.5):
-                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*):
@@ -172,7 +172,7 @@ class TextInpainting(DiffusionPipeline, StableDiffusionMixin):
             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
+                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`, *optional*):
                 A [torch generator](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation

examples/community/tiled_upscaling.py

@@ -212,9 +212,9 @@ class StableDiffusionTiledUpscalePipeline(StableDiffusionUpscalePipeline):
                 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 7.5):
-                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*):
@@ -223,7 +223,7 @@ class StableDiffusionTiledUpscalePipeline(StableDiffusionUpscalePipeline):
             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
+                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`, *optional*):
                 A [torch generator](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation

examples/community/unclip_image_interpolation.py

@@ -247,9 +247,9 @@ class UnCLIPImageInterpolationPipeline(DiffusionPipeline):
             super_res_latents (`torch.Tensor` of shape (batch size, channels, super res height, super res width), *optional*):
                 Pre-generated noisy latents to be used as inputs for the decoder.
             decoder_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.
             output_type (`str`, *optional*, defaults to `"pil"`):

examples/community/unclip_text_interpolation.py

@@ -252,15 +252,15 @@ class UnCLIPTextInterpolationPipeline(DiffusionPipeline):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
             prior_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.
             decoder_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.
             output_type (`str`, *optional*, defaults to `"pil"`):

examples/community/wildcard_stable_diffusion.py

@@ -190,9 +190,9 @@ class WildcardStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
                 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 7.5):
-                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*):
@@ -201,7 +201,7 @@ class WildcardStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
             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
+                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`, *optional*):
                 A [torch generator](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation
@@ -288,7 +288,7 @@ class WildcardStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
         text_embeddings = text_embeddings.view(bs_embed * num_images_per_prompt, seq_len, -1)
 
         # 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
         # get unconditional embeddings for classifier free guidance
@@ -364,7 +364,7 @@ class WildcardStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
 
         # 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_step_kwargs = {}

examples/consistency_distillation/README.md

 # Latent Consistency Distillation Example:
 
-[Latent Consistency Models (LCMs)](https://arxiv.org/abs/2310.04378) is a method to distill a latent diffusion model to enable swift inference with minimal steps. This example demonstrates how to use latent consistency distillation to distill stable-diffusion-v1.5 for inference with few timesteps.
+[Latent Consistency Models (LCMs)](https://huggingface.co/papers/2310.04378) is a method to distill a latent diffusion model to enable swift inference with minimal steps. This example demonstrates how to use latent consistency distillation to distill stable-diffusion-v1.5 for inference with few timesteps.
 
 ## Full model distillation
 

examples/consistency_distillation/README_sdxl.md

 # Latent Consistency Distillation Example:
 
-[Latent Consistency Models (LCMs)](https://arxiv.org/abs/2310.04378) is a method to distill a latent diffusion model to enable swift inference with minimal steps. This example demonstrates how to use latent consistency distillation to distill SDXL for inference with few timesteps.
+[Latent Consistency Models (LCMs)](https://huggingface.co/papers/2310.04378) is a method to distill a latent diffusion model to enable swift inference with minimal steps. This example demonstrates how to use latent consistency distillation to distill SDXL for inference with few timesteps.
 
 ## Full model distillation
 

examples/controlnet/README.md

 # ControlNet training example
 
-[Adding Conditional Control to Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.05543) by Lvmin Zhang and Maneesh Agrawala.
+[Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang and Maneesh Agrawala.
 
 This example is based on the [training example in the original ControlNet repository](https://github.com/lllyasviel/ControlNet/blob/main/docs/train.md). It trains a ControlNet to fill circles using a [small synthetic dataset](https://huggingface.co/datasets/fusing/fill50k).
 
@@ -437,7 +437,7 @@ You can then start your training from this saved checkpoint with
  --controlnet_model_name_or_path="./control_out/500"
 ```
 
-We support training with the Min-SNR weighting strategy proposed in [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://arxiv.org/abs/2303.09556) which helps to achieve faster convergence by rebalancing the loss. To use it, one needs to set the `--snr_gamma` argument. The recommended value when using it is `5.0`.
+We support training with the Min-SNR weighting strategy proposed in [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://huggingface.co/papers/2303.09556) which helps to achieve faster convergence by rebalancing the loss. To use it, one needs to set the `--snr_gamma` argument. The recommended value when using it is `5.0`.
 
 We also support gradient accumulation - it is a technique that lets you use a bigger batch size than your machine would normally be able to fit into memory. You can use `gradient_accumulation_steps` argument to set gradient accumulation steps. The ControlNet author recommends using gradient accumulation to achieve better convergence. Read more [here](https://github.com/lllyasviel/ControlNet/blob/main/docs/train.md#more-consideration-sudden-converge-phenomenon-and-gradient-accumulation).
 

examples/controlnet/README_sd3.md

 # ControlNet training example for Stable Diffusion 3/3.5 (SD3/3.5)
 
-The `train_controlnet_sd3.py` script shows how to implement the ControlNet training procedure and adapt it for [Stable Diffusion 3](https://arxiv.org/abs/2403.03206) and [Stable Diffusion 3.5](https://stability.ai/news/introducing-stable-diffusion-3-5).
+The `train_controlnet_sd3.py` script shows how to implement the ControlNet training procedure and adapt it for [Stable Diffusion 3](https://huggingface.co/papers/2403.03206) and [Stable Diffusion 3.5](https://stability.ai/news/introducing-stable-diffusion-3-5).
 
 ## Running locally with PyTorch
 

examples/controlnet/train_controlnet_flax.py

@@ -305,7 +305,7 @@ def parse_args():
         type=float,
         default=None,
         help="SNR weighting gamma to be used if rebalancing the loss. Recommended value is 5.0. "
-        "More details here: https://arxiv.org/abs/2303.09556.",
+        "More details here: https://huggingface.co/papers/2303.09556.",
     )
     parser.add_argument(
         "--dataloader_num_workers",

examples/controlnet/train_controlnet_sd3.py

@@ -1352,7 +1352,7 @@ def main(args):
                     return_dict=False,
                 )[0]
 
-                # Follow: Section 5 of https://arxiv.org/abs/2206.00364.
+                # Follow: Section 5 of https://huggingface.co/papers/2206.00364.
                 # Preconditioning of the model outputs.
                 if args.precondition_outputs:
                     model_pred = model_pred * (-sigmas) + noisy_model_input

examples/custom_diffusion/README.md

 # Custom Diffusion training example
 
-[Custom Diffusion](https://arxiv.org/abs/2212.04488) is a method to customize text-to-image models like Stable Diffusion given just a few (4~5) images of a subject.
+[Custom Diffusion](https://huggingface.co/papers/2212.04488) is a method to customize text-to-image models like Stable Diffusion given just a few (4~5) images of a subject.
 The `train_custom_diffusion.py` script shows how to implement the training procedure and adapt it for stable diffusion.
 
 ## Running locally with PyTorch

examples/dreambooth/README.md

 # DreamBooth training example
 
-[DreamBooth](https://arxiv.org/abs/2208.12242) is a method to personalize text2image models like stable diffusion given just a few(3~5) images of a subject.
+[DreamBooth](https://huggingface.co/papers/2208.12242) is a method to personalize text2image models like stable diffusion given just a few(3~5) images of a subject.
 The `train_dreambooth.py` script shows how to implement the training procedure and adapt it for stable diffusion.
 
 
@@ -296,7 +296,7 @@ You can also perform inference from one of the checkpoints saved during the trai
 
 ## Training with Low-Rank Adaptation of Large Language Models (LoRA)
 
-Low-Rank Adaption of Large Language Models was first introduced by Microsoft in [LoRA: Low-Rank Adaptation of Large Language Models](https://arxiv.org/abs/2106.09685) by *Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen*
+Low-Rank Adaption of Large Language Models was first introduced by Microsoft in [LoRA: Low-Rank Adaptation of Large Language Models](https://huggingface.co/papers/2106.09685) by *Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen*
 
 In a nutshell, LoRA allows to adapt pretrained models by adding pairs of rank-decomposition matrices to existing weights and **only** training those newly added weights. This has a couple of advantages:
 - Previous pretrained weights are kept frozen so that the model is not prone to [catastrophic forgetting](https://www.pnas.org/doi/10.1073/pnas.1611835114)