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/pipeline_stg_hunyuan_video.py

@@ -583,9 +583,9 @@ class HunyuanVideoSTGPipeline(DiffusionPipeline, HunyuanVideoLoraLoaderMixin):
                 their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
                 will be used.
             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. Note that the only available HunyuanVideo model is
                 CFG-distilled, which means that traditional guidance between unconditional and conditional latent is

examples/community/pipeline_stg_ltx.py

@@ -607,9 +607,9 @@ class LTXSTGPipeline(DiffusionPipeline, FromSingleFileMixin, LTXVideoLoraLoaderM
                 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`, defaults to `3 `):
-                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):

examples/community/pipeline_stg_ltx_image2video.py

@@ -669,9 +669,9 @@ class LTXImageToVideoSTGPipeline(DiffusionPipeline, FromSingleFileMixin, LTXVide
                 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`, defaults to `3 `):
-                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):

examples/community/pipeline_stg_mochi.py

@@ -590,9 +590,9 @@ class MochiSTGPipeline(DiffusionPipeline, Mochi1LoraLoaderMixin):
                 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`, defaults to `4.5`):
-                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.
             num_videos_per_prompt (`int`, *optional*, defaults to 1):

examples/community/pipeline_stg_wan.py

@@ -451,9 +451,9 @@ class WanSTGPipeline(DiffusionPipeline, WanLoraLoaderMixin):
                 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):

examples/community/pipeline_zero1to3.py

@@ -464,7 +464,7 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
     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())
@@ -637,9 +637,9 @@ class Zero1to3StableDiffusionPipeline(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*):
@@ -649,7 +649,7 @@ class Zero1to3StableDiffusionPipeline(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` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
@@ -708,7 +708,7 @@ class Zero1to3StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
             batch_size = input_imgs.shape[0]
         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/rerender_a_video.py

@@ -99,7 +99,7 @@ def flow_warp(feature, flow, mask=False, mode="bilinear", padding_mode="zeros"):
 def forward_backward_consistency_check(fwd_flow, bwd_flow, alpha=0.01, beta=0.5):
     # fwd_flow, bwd_flow: [B, 2, H, W]
     # alpha and beta values are following UnFlow
-    # (https://arxiv.org/abs/1711.07837)
+    # (https://huggingface.co/papers/1711.07837)
     assert fwd_flow.dim() == 4 and bwd_flow.dim() == 4
     assert fwd_flow.size(1) == 2 and bwd_flow.size(1) == 2
     flow_mag = torch.norm(fwd_flow, dim=1) + torch.norm(bwd_flow, dim=1)  # [B, H, W]
@@ -638,9 +638,9 @@ class RerenderAVideoPipeline(StableDiffusionControlNetImg2ImgPipeline):
                 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*):
@@ -648,7 +648,7 @@ class RerenderAVideoPipeline(StableDiffusionControlNetImg2ImgPipeline):
                 `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                 less than `1`).
             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)
@@ -747,7 +747,7 @@ class RerenderAVideoPipeline(StableDiffusionControlNetImg2ImgPipeline):
 
         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/run_onnx_controlnet.py

@@ -252,7 +252,7 @@ class OnnxStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
     def prepare_extra_step_kwargs(self, generator, eta):
         # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
         # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
+        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
         # and should be between [0, 1]
 
         accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
@@ -571,9 +571,9 @@ class OnnxStableDiffusionControlNetImg2ImgPipeline(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*):
@@ -583,7 +583,7 @@ class OnnxStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
             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)
@@ -680,7 +680,7 @@ class OnnxStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
 
         device = self._execution_device
         # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+        # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
         # corresponds to doing no classifier free guidance.
         do_classifier_free_guidance = guidance_scale > 1.0
 

examples/community/run_tensorrt_controlnet.py

@@ -356,7 +356,7 @@ class TensorRTStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
     def prepare_extra_step_kwargs(self, generator, eta):
         # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
         # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
+        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
         # and should be between [0, 1]
 
         accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
@@ -675,9 +675,9 @@ class TensorRTStableDiffusionControlNetImg2ImgPipeline(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*):
@@ -687,7 +687,7 @@ class TensorRTStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
             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)
@@ -784,7 +784,7 @@ class TensorRTStableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
 
         device = self._execution_device
         # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+        # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
         # corresponds to doing no classifier free guidance.
         do_classifier_free_guidance = guidance_scale > 1.0
 

examples/community/scheduling_ufogen.py

@@ -94,7 +94,7 @@ def betas_for_alpha_bar(
 # Copied from diffusers.schedulers.scheduling_ddim.rescale_zero_terminal_snr
 def rescale_zero_terminal_snr(betas):
     """
-    Rescales betas to have zero terminal SNR Based on https://arxiv.org/pdf/2305.08891.pdf (Algorithm 1)
+    Rescales betas to have zero terminal SNR Based on https://huggingface.co/papers/2305.08891 (Algorithm 1)
 
 
     Args:
@@ -131,7 +131,7 @@ def rescale_zero_terminal_snr(betas):
 class UFOGenScheduler(SchedulerMixin, ConfigMixin):
     """
     `UFOGenScheduler` implements multistep and onestep sampling for a UFOGen model, introduced in
-    [UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs](https://arxiv.org/abs/2311.09257)
+    [UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs](https://huggingface.co/papers/2311.09257)
     by Yanwu Xu, Yang Zhao, Zhisheng Xiao, and Tingbo Hou. UFOGen is a varianet of the denoising diffusion GAN (DDGAN)
     model designed for one-step sampling.
 
@@ -311,7 +311,7 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
                 timesteps = np.array([self.config.num_train_timesteps - 1], dtype=np.int64)
             else:
                 # TODO: For now, retain the DDPM timestep spacing logic
-                # "linspace", "leading", "trailing" corresponds to annotation of Table 2. of https://arxiv.org/abs/2305.08891
+                # "linspace", "leading", "trailing" corresponds to annotation of Table 2. of https://huggingface.co/papers/2305.08891
                 if self.config.timestep_spacing == "linspace":
                     timesteps = (
                         np.linspace(0, self.config.num_train_timesteps - 1, num_inference_steps)
@@ -347,7 +347,7 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
         pixels from saturation at each step. We find that dynamic thresholding results in significantly better
         photorealism as well as better image-text alignment, especially when using very large guidance weights."
 
-        https://arxiv.org/abs/2205.11487
+        https://huggingface.co/papers/2205.11487
         """
         dtype = sample.dtype
         batch_size, channels, *remaining_dims = sample.shape
@@ -415,7 +415,7 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
         # current_beta_t = 1 - current_alpha_t
 
         # 2. compute predicted original sample from predicted noise also called
-        # "predicted x_0" of formula (15) from https://arxiv.org/pdf/2006.11239.pdf
+        # "predicted x_0" of formula (15) from https://huggingface.co/papers/2006.11239
         if self.config.prediction_type == "epsilon":
             pred_original_sample = (sample - beta_prod_t ** (0.5) * model_output) / alpha_prod_t ** (0.5)
         elif self.config.prediction_type == "sample":

examples/community/sd_text2img_k_diffusion.py

@@ -307,9 +307,9 @@ class StableDiffusionPipeline(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*):
@@ -318,7 +318,7 @@ class StableDiffusionPipeline(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
@@ -355,7 +355,7 @@ class StableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
         batch_size = 1 if isinstance(prompt, str) else len(prompt)
         device = self._execution_device
         # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+        # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
         # corresponds to doing no classifier free guidance.
         do_classifier_free_guidance = True
         if guidance_scale <= 1.0:

examples/community/sde_drag.py

@@ -25,7 +25,7 @@ from diffusers.optimization import get_scheduler
 
 class SdeDragPipeline(DiffusionPipeline):
     r"""
-    Pipeline for image drag-and-drop editing using stochastic differential equations: https://arxiv.org/abs/2311.01410.
+    Pipeline for image drag-and-drop editing using stochastic differential equations: https://huggingface.co/papers/2311.01410.
     Please refer to the [official repository](https://github.com/ML-GSAI/SDE-Drag) for more information.
 
     This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the

examples/community/seed_resize_stable_diffusion.py

@@ -103,9 +103,9 @@ class SeedResizeStableDiffusionPipeline(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*):
@@ -114,7 +114,7 @@ class SeedResizeStableDiffusionPipeline(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
@@ -188,7 +188,7 @@ class SeedResizeStableDiffusionPipeline(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
@@ -287,7 +287,7 @@ class SeedResizeStableDiffusionPipeline(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/community/speech_to_image_diffusion.py

@@ -134,7 +134,7 @@ class SpeechToImagePipeline(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
@@ -210,7 +210,7 @@ class SpeechToImagePipeline(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/community/stable_diffusion_comparison.py

@@ -265,13 +265,13 @@ class StableDiffusionComparisonPipeline(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.
             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/stable_diffusion_controlnet_img2img.py

@@ -340,7 +340,7 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusio
     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())
@@ -651,9 +651,9 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusio
                 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*):
@@ -662,7 +662,7 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusio
             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)
@@ -742,7 +742,7 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusio
 
         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_controlnet_inpaint.py

@@ -439,7 +439,7 @@ class StableDiffusionControlNetInpaintPipeline(DiffusionPipeline, StableDiffusio
     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())
@@ -791,9 +791,9 @@ class StableDiffusionControlNetInpaintPipeline(DiffusionPipeline, StableDiffusio
                 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*):
@@ -802,7 +802,7 @@ class StableDiffusionControlNetInpaintPipeline(DiffusionPipeline, StableDiffusio
             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)
@@ -875,7 +875,7 @@ class StableDiffusionControlNetInpaintPipeline(DiffusionPipeline, StableDiffusio
 
         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_controlnet_inpaint_img2img.py

@@ -424,7 +424,7 @@ class StableDiffusionControlNetInpaintImg2ImgPipeline(DiffusionPipeline, StableD
     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())
@@ -785,9 +785,9 @@ class StableDiffusionControlNetInpaintImg2ImgPipeline(DiffusionPipeline, StableD
                 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*):
@@ -796,7 +796,7 @@ class StableDiffusionControlNetInpaintImg2ImgPipeline(DiffusionPipeline, StableD
             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)
@@ -869,7 +869,7 @@ class StableDiffusionControlNetInpaintImg2ImgPipeline(DiffusionPipeline, StableD
 
         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_controlnet_reference.py

@@ -159,9 +159,9 @@ class StableDiffusionControlNetReferencePipeline(StableDiffusionControlNetPipeli
                 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*):
@@ -171,7 +171,7 @@ class StableDiffusionControlNetReferencePipeline(StableDiffusionControlNetPipeli
             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)
@@ -255,7 +255,7 @@ class StableDiffusionControlNetReferencePipeline(StableDiffusionControlNetPipeli
 
         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_ipex.py

@@ -210,7 +210,7 @@ class StableDiffusionIPEXPipeline(
 
         device = "cpu"
         # 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
 
@@ -475,7 +475,7 @@ class StableDiffusionIPEXPipeline(
     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())
@@ -595,9 +595,9 @@ class StableDiffusionIPEXPipeline(
                 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*):
@@ -607,7 +607,7 @@ class StableDiffusionIPEXPipeline(
             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)
@@ -668,7 +668,7 @@ class StableDiffusionIPEXPipeline(
 
         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