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

diffusers/schedulers/scheduling_ddpm_flax.py

@@ -1,4 +1,4 @@
-# Copyright 2024 UC Berkeley Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 UC Berkeley Team and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -61,7 +61,7 @@ class FlaxDDPMScheduler(FlaxSchedulerMixin, ConfigMixin):
     [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and
     [`~SchedulerMixin.from_pretrained`] functions.
 
-    For more details, see the original paper: https://arxiv.org/abs/2006.11239
+    For more details, see the original paper: https://huggingface.co/papers/2006.11239
 
     Args:
         num_train_timesteps (`int`): number of diffusion steps used to train the model.
@@ -163,7 +163,7 @@ class FlaxDDPMScheduler(FlaxSchedulerMixin, ConfigMixin):
         alpha_prod_t = state.common.alphas_cumprod[t]
         alpha_prod_t_prev = jnp.where(t > 0, state.common.alphas_cumprod[t - 1], jnp.array(1.0, dtype=self.dtype))
 
-        # For t > 0, compute predicted variance βt (see formula (6) and (7) from https://arxiv.org/pdf/2006.11239.pdf)
+        # For t > 0, compute predicted variance βt (see formula (6) and (7) from https://huggingface.co/papers/2006.11239)
         # and sample from it to get previous sample
         # x_{t-1} ~ N(pred_prev_sample, variance) == add variance to pred_sample
         variance = (1 - alpha_prod_t_prev) / (1 - alpha_prod_t) * state.common.betas[t]
@@ -174,7 +174,7 @@ class FlaxDDPMScheduler(FlaxSchedulerMixin, ConfigMixin):
         # hacks - were probably added for training stability
         if variance_type == "fixed_small":
             variance = jnp.clip(variance, a_min=1e-20)
-        # for rl-diffuser https://arxiv.org/abs/2205.09991
+        # for rl-diffuser https://huggingface.co/papers/2205.09991
         elif variance_type == "fixed_small_log":
             variance = jnp.log(jnp.clip(variance, a_min=1e-20))
         elif variance_type == "fixed_large":
@@ -240,7 +240,7 @@ class FlaxDDPMScheduler(FlaxSchedulerMixin, ConfigMixin):
         beta_prod_t_prev = 1 - alpha_prod_t_prev
 
         # 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":
@@ -258,12 +258,12 @@ class FlaxDDPMScheduler(FlaxSchedulerMixin, ConfigMixin):
             pred_original_sample = jnp.clip(pred_original_sample, -1, 1)
 
         # 4. Compute coefficients for pred_original_sample x_0 and current sample x_t
-        # See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
+        # See formula (7) from https://huggingface.co/papers/2006.11239
         pred_original_sample_coeff = (alpha_prod_t_prev ** (0.5) * state.common.betas[t]) / beta_prod_t
         current_sample_coeff = state.common.alphas[t] ** (0.5) * beta_prod_t_prev / beta_prod_t
 
         # 5. Compute predicted previous sample µ_t
-        # See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
+        # See formula (7) from https://huggingface.co/papers/2006.11239
         pred_prev_sample = pred_original_sample_coeff * pred_original_sample + current_sample_coeff * sample
 
         # 6. Add noise

diffusers/schedulers/scheduling_ddpm_parallel.py

@@ -1,4 +1,4 @@
-# Copyright 2024 ParaDiGMS authors and The HuggingFace Team. All rights reserved.
+# Copyright 2025 ParaDiGMS authors and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -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:
@@ -138,7 +138,7 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
     [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and
     [`~SchedulerMixin.from_pretrained`] functions.
 
-    For more details, see the original paper: https://arxiv.org/abs/2006.11239
+    For more details, see the original paper: https://huggingface.co/papers/2006.11239
 
     Args:
         num_train_timesteps (`int`): number of diffusion steps used to train the model.
@@ -161,17 +161,17 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
             process), `sample` (directly predicting the noisy sample`) or `v_prediction` (see section 2.4
             https://imagen.research.google/video/paper.pdf)
         thresholding (`bool`, default `False`):
-            whether to use the "dynamic thresholding" method (introduced by Imagen, https://arxiv.org/abs/2205.11487).
-            Note that the thresholding method is unsuitable for latent-space diffusion models (such as
-            stable-diffusion).
+            whether to use the "dynamic thresholding" method (introduced by Imagen,
+            https://huggingface.co/papers/2205.11487). Note that the thresholding method is unsuitable for latent-space
+            diffusion models (such as stable-diffusion).
         dynamic_thresholding_ratio (`float`, default `0.995`):
             the ratio for the dynamic thresholding method. Default is `0.995`, the same as Imagen
-            (https://arxiv.org/abs/2205.11487). Valid only when `thresholding=True`.
+            (https://huggingface.co/papers/2205.11487). Valid only when `thresholding=True`.
         sample_max_value (`float`, default `1.0`):
             the threshold value for dynamic thresholding. Valid only when `thresholding=True`.
         timestep_spacing (`str`, default `"leading"`):
             The way the timesteps should be scaled. Refer to Table 2. of [Common Diffusion Noise Schedules and Sample
-            Steps are Flawed](https://arxiv.org/abs/2305.08891) for more information.
+            Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
         steps_offset (`int`, default `0`):
             An offset added to the inference steps, as required by some model families.
         rescale_betas_zero_snr (`bool`, defaults to `False`):
@@ -305,7 +305,7 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
             self.num_inference_steps = num_inference_steps
             self.custom_timesteps = False
 
-            # "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)
@@ -340,7 +340,7 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         alpha_prod_t_prev = self.alphas_cumprod[prev_t] if prev_t >= 0 else self.one
         current_beta_t = 1 - alpha_prod_t / alpha_prod_t_prev
 
-        # For t > 0, compute predicted variance βt (see formula (6) and (7) from https://arxiv.org/pdf/2006.11239.pdf)
+        # For t > 0, compute predicted variance βt (see formula (6) and (7) from https://huggingface.co/papers/2006.11239)
         # and sample from it to get previous sample
         # x_{t-1} ~ N(pred_prev_sample, variance) == add variance to pred_sample
         variance = (1 - alpha_prod_t_prev) / (1 - alpha_prod_t) * current_beta_t
@@ -354,7 +354,7 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         # hacks - were probably added for training stability
         if variance_type == "fixed_small":
             variance = variance
-        # for rl-diffuser https://arxiv.org/abs/2205.09991
+        # for rl-diffuser https://huggingface.co/papers/2205.09991
         elif variance_type == "fixed_small_log":
             variance = torch.log(variance)
             variance = torch.exp(0.5 * variance)
@@ -382,7 +382,7 @@ class DDPMParallelScheduler(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
@@ -451,7 +451,7 @@ class DDPMParallelScheduler(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":
@@ -473,12 +473,12 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
             )
 
         # 4. Compute coefficients for pred_original_sample x_0 and current sample x_t
-        # See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
+        # See formula (7) from https://huggingface.co/papers/2006.11239
         pred_original_sample_coeff = (alpha_prod_t_prev ** (0.5) * current_beta_t) / beta_prod_t
         current_sample_coeff = current_alpha_t ** (0.5) * beta_prod_t_prev / beta_prod_t
 
         # 5. Compute predicted previous sample µ_t
-        # See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
+        # See formula (7) from https://huggingface.co/papers/2006.11239
         pred_prev_sample = pred_original_sample_coeff * pred_original_sample + current_sample_coeff * sample
 
         # 6. Add noise
@@ -554,7 +554,7 @@ class DDPMParallelScheduler(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":
@@ -576,12 +576,12 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
             )
 
         # 4. Compute coefficients for pred_original_sample x_0 and current sample x_t
-        # See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
+        # See formula (7) from https://huggingface.co/papers/2006.11239
         pred_original_sample_coeff = (alpha_prod_t_prev ** (0.5) * current_beta_t) / beta_prod_t
         current_sample_coeff = current_alpha_t ** (0.5) * beta_prod_t_prev / beta_prod_t
 
         # 5. Compute predicted previous sample µ_t
-        # See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
+        # See formula (7) from https://huggingface.co/papers/2006.11239
         pred_prev_sample = pred_original_sample_coeff * pred_original_sample + current_sample_coeff * sample
 
         return pred_prev_sample

diffusers/schedulers/scheduling_ddpm_wuerstchen.py

@@ -1,5 +1,5 @@
 # Copyright (c) 2022 Pablo Pernías MIT License
-# Copyright 2024 UC Berkeley Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 UC Berkeley Team and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -95,7 +95,7 @@ class DDPMWuerstchenScheduler(SchedulerMixin, ConfigMixin):
     [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and
     [`~SchedulerMixin.from_pretrained`] functions.
 
-    For more details, see the original paper: https://arxiv.org/abs/2006.11239
+    For more details, see the original paper: https://huggingface.co/papers/2006.11239
 
     Args:
         scaler (`float`): ....

diffusers/schedulers/scheduling_deis_multistep.py

@@ -1,4 +1,4 @@
-# Copyright 2024 FLAIR Lab and The HuggingFace Team. All rights reserved.
+# Copyright 2025 FLAIR Lab and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# DISCLAIMER: check https://arxiv.org/abs/2204.13902 and https://github.com/qsh-zh/deis for more info
+# DISCLAIMER: check https://huggingface.co/papers/2204.13902 and https://github.com/qsh-zh/deis for more info
 # The codebase is modified based on https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py
 
 import math
@@ -242,7 +242,7 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
             device (`str` or `torch.device`, *optional*):
                 The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
         """
-        # "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 + 1)
@@ -319,7 +319,7 @@ class DEISMultistepScheduler(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
@@ -486,7 +486,7 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 1:
                 sample = args[1]
             else:
-                raise ValueError("missing `sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep is not None:
             deprecate(
                 "timesteps",
@@ -549,7 +549,7 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 2:
                 sample = args[2]
             else:
-                raise ValueError(" missing `sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep is not None:
             deprecate(
                 "timesteps",
@@ -603,7 +603,7 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 2:
                 sample = args[2]
             else:
-                raise ValueError(" missing `sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep_list is not None:
             deprecate(
                 "timestep_list",
@@ -673,7 +673,7 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 2:
                 sample = args[2]
             else:
-                raise ValueError(" missing`sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep_list is not None:
             deprecate(
                 "timestep_list",

diffusers/schedulers/scheduling_dpm_cogvideox.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The CogVideoX team, Tsinghua University & ZhipuAI and The HuggingFace Team.
+# Copyright 2025 The CogVideoX team, Tsinghua University & ZhipuAI and The HuggingFace Team.
 # All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -95,7 +95,7 @@ def betas_for_alpha_bar(
 
 def rescale_zero_terminal_snr(alphas_cumprod):
     """
-    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:
@@ -276,7 +276,7 @@ class CogVideoXDPMScheduler(SchedulerMixin, ConfigMixin):
 
         self.num_inference_steps = num_inference_steps
 
-        # "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)
@@ -377,7 +377,7 @@ class CogVideoXDPMScheduler(SchedulerMixin, ConfigMixin):
                 "Number of inference steps is 'None', you need to run 'set_timesteps' after creating the scheduler"
             )
 
-        # See formulas (12) and (16) of DDIM paper https://arxiv.org/pdf/2010.02502.pdf
+        # See formulas (12) and (16) of DDIM paper https://huggingface.co/papers/2010.02502
         # Ideally, read DDIM paper in-detail understanding
 
         # Notation (<variable name> -> <name in paper>
@@ -399,7 +399,7 @@ class CogVideoXDPMScheduler(SchedulerMixin, ConfigMixin):
         beta_prod_t = 1 - alpha_prod_t
 
         # 3. compute predicted original sample from predicted noise also called
-        # "predicted x_0" of formula (12) from https://arxiv.org/pdf/2010.02502.pdf
+        # "predicted x_0" of formula (12) from https://huggingface.co/papers/2010.02502
         # To make style tests pass, commented out `pred_epsilon` as it is an unused variable
         if self.config.prediction_type == "epsilon":
             pred_original_sample = (sample - beta_prod_t ** (0.5) * model_output) / alpha_prod_t ** (0.5)

diffusers/schedulers/scheduling_dpmsolver_multistep.py

@@ -1,4 +1,4 @@
-# Copyright 2024 TSAIL Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 TSAIL Team and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -78,7 +78,7 @@ 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:
@@ -366,7 +366,7 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
             clipped_idx = torch.searchsorted(torch.flip(self.lambda_t, [0]), self.config.lambda_min_clipped)
             last_timestep = ((self.config.num_train_timesteps - clipped_idx).numpy()).item()
 
-            # "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, last_timestep - 1, num_inference_steps + 1)
@@ -460,7 +460,7 @@ class DPMSolverMultistepScheduler(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
@@ -646,7 +646,7 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 1:
                 sample = args[1]
             else:
-                raise ValueError("missing `sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep is not None:
             deprecate(
                 "timesteps",
@@ -741,7 +741,7 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 2:
                 sample = args[2]
             else:
-                raise ValueError(" missing `sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep is not None:
             deprecate(
                 "timesteps",
@@ -810,7 +810,7 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 2:
                 sample = args[2]
             else:
-                raise ValueError(" missing `sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep_list is not None:
             deprecate(
                 "timestep_list",
@@ -845,7 +845,7 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
         r0 = h_0 / h
         D0, D1 = m0, (1.0 / r0) * (m0 - m1)
         if self.config.algorithm_type == "dpmsolver++":
-            # See https://arxiv.org/abs/2211.01095 for detailed derivations
+            # See https://huggingface.co/papers/2211.01095 for detailed derivations
             if self.config.solver_type == "midpoint":
                 x_t = (
                     (sigma_t / sigma_s0) * sample
@@ -859,7 +859,7 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
                     + (alpha_t * ((torch.exp(-h) - 1.0) / h + 1.0)) * D1
                 )
         elif self.config.algorithm_type == "dpmsolver":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
+            # See https://huggingface.co/papers/2206.00927 for detailed derivations
             if self.config.solver_type == "midpoint":
                 x_t = (
                     (alpha_t / alpha_s0) * sample
@@ -934,7 +934,7 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 2:
                 sample = args[2]
             else:
-                raise ValueError(" missing`sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep_list is not None:
             deprecate(
                 "timestep_list",
@@ -975,7 +975,7 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
         D1 = D1_0 + (r0 / (r0 + r1)) * (D1_0 - D1_1)
         D2 = (1.0 / (r0 + r1)) * (D1_0 - D1_1)
         if self.config.algorithm_type == "dpmsolver++":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
+            # See https://huggingface.co/papers/2206.00927 for detailed derivations
             x_t = (
                 (sigma_t / sigma_s0) * sample
                 - (alpha_t * (torch.exp(-h) - 1.0)) * D0
@@ -983,7 +983,7 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
                 - (alpha_t * ((torch.exp(-h) - 1.0 + h) / h**2 - 0.5)) * D2
             )
         elif self.config.algorithm_type == "dpmsolver":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
+            # See https://huggingface.co/papers/2206.00927 for detailed derivations
             x_t = (
                 (alpha_t / alpha_s0) * sample
                 - (sigma_t * (torch.exp(h) - 1.0)) * D0

diffusers/schedulers/scheduling_dpmsolver_multistep_flax.py

@@ -1,4 +1,4 @@
-# Copyright 2024 TSAIL Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 TSAIL Team and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -80,14 +80,15 @@ class FlaxDPMSolverMultistepScheduler(FlaxSchedulerMixin, ConfigMixin):
     the convergence order guarantee. Empirically, sampling by DPM-Solver with only 20 steps can generate high-quality
     samples, and it can generate quite good samples even in only 10 steps.
 
-    For more details, see the original paper: https://arxiv.org/abs/2206.00927 and https://arxiv.org/abs/2211.01095
+    For more details, see the original paper: https://huggingface.co/papers/2206.00927 and
+    https://huggingface.co/papers/2211.01095
 
     Currently, we support the multistep DPM-Solver for both noise prediction models and data prediction models. We
     recommend to use `solver_order=2` for guided sampling, and `solver_order=3` for unconditional sampling.
 
-    We also support the "dynamic thresholding" method in Imagen (https://arxiv.org/abs/2205.11487). For pixel-space
-    diffusion models, you can set both `algorithm_type="dpmsolver++"` and `thresholding=True` to use the dynamic
-    thresholding. Note that the thresholding method is unsuitable for latent-space diffusion models (such as
+    We also support the "dynamic thresholding" method in Imagen (https://huggingface.co/papers/2205.11487). For
+    pixel-space diffusion models, you can set both `algorithm_type="dpmsolver++"` and `thresholding=True` to use the
+    dynamic thresholding. Note that the thresholding method is unsuitable for latent-space diffusion models (such as
     stable-diffusion).
 
     [`~ConfigMixin`] takes care of storing all config attributes that are passed in the scheduler's `__init__`
@@ -95,7 +96,8 @@ class FlaxDPMSolverMultistepScheduler(FlaxSchedulerMixin, ConfigMixin):
     [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and
     [`~SchedulerMixin.from_pretrained`] functions.
 
-    For more details, see the original paper: https://arxiv.org/abs/2206.00927 and https://arxiv.org/abs/2211.01095
+    For more details, see the original paper: https://huggingface.co/papers/2206.00927 and
+    https://huggingface.co/papers/2211.01095
 
     Args:
         num_train_timesteps (`int`): number of diffusion steps used to train the model.
@@ -113,21 +115,21 @@ class FlaxDPMSolverMultistepScheduler(FlaxSchedulerMixin, ConfigMixin):
             indicates whether the model predicts the noise (epsilon), or the data / `x0`. One of `epsilon`, `sample`,
             or `v-prediction`.
         thresholding (`bool`, default `False`):
-            whether to use the "dynamic thresholding" method (introduced by Imagen, https://arxiv.org/abs/2205.11487).
-            For pixel-space diffusion models, you can set both `algorithm_type=dpmsolver++` and `thresholding=True` to
-            use the dynamic thresholding. Note that the thresholding method is unsuitable for latent-space diffusion
-            models (such as stable-diffusion).
+            whether to use the "dynamic thresholding" method (introduced by Imagen,
+            https://huggingface.co/papers/2205.11487). For pixel-space diffusion models, you can set both
+            `algorithm_type=dpmsolver++` and `thresholding=True` to use the dynamic thresholding. Note that the
+            thresholding method is unsuitable for latent-space diffusion models (such as stable-diffusion).
         dynamic_thresholding_ratio (`float`, default `0.995`):
             the ratio for the dynamic thresholding method. Default is `0.995`, the same as Imagen
-            (https://arxiv.org/abs/2205.11487).
+            (https://huggingface.co/papers/2205.11487).
         sample_max_value (`float`, default `1.0`):
             the threshold value for dynamic thresholding. Valid only when `thresholding=True` and
             `algorithm_type="dpmsolver++`.
         algorithm_type (`str`, default `dpmsolver++`):
             the algorithm type for the solver. Either `dpmsolver` or `dpmsolver++`. The `dpmsolver` type implements the
-            algorithms in https://arxiv.org/abs/2206.00927, and the `dpmsolver++` type implements the algorithms in
-            https://arxiv.org/abs/2211.01095. We recommend to use `dpmsolver++` with `solver_order=2` for guided
-            sampling (e.g. stable-diffusion).
+            algorithms in https://huggingface.co/papers/2206.00927, and the `dpmsolver++` type implements the
+            algorithms in https://huggingface.co/papers/2211.01095. We recommend to use `dpmsolver++` with
+            `solver_order=2` for guided sampling (e.g. stable-diffusion).
         solver_type (`str`, default `midpoint`):
             the solver type for the second-order solver. Either `midpoint` or `heun`. The solver type slightly affects
             the sample quality, especially for small number of steps. We empirically find that `midpoint` solvers are
@@ -297,7 +299,7 @@ class FlaxDPMSolverMultistepScheduler(FlaxSchedulerMixin, ConfigMixin):
                 )
 
             if self.config.thresholding:
-                # Dynamic thresholding in https://arxiv.org/abs/2205.11487
+                # Dynamic thresholding in https://huggingface.co/papers/2205.11487
                 dynamic_max_val = jnp.percentile(
                     jnp.abs(x0_pred), self.config.dynamic_thresholding_ratio, axis=tuple(range(1, x0_pred.ndim))
                 )
@@ -335,7 +337,7 @@ class FlaxDPMSolverMultistepScheduler(FlaxSchedulerMixin, ConfigMixin):
         """
         One step for the first-order DPM-Solver (equivalent to DDIM).
 
-        See https://arxiv.org/abs/2206.00927 for the detailed derivation.
+        See https://huggingface.co/papers/2206.00927 for the detailed derivation.
 
         Args:
             model_output (`jnp.ndarray`): direct output from learned diffusion model.
@@ -390,7 +392,7 @@ class FlaxDPMSolverMultistepScheduler(FlaxSchedulerMixin, ConfigMixin):
         r0 = h_0 / h
         D0, D1 = m0, (1.0 / r0) * (m0 - m1)
         if self.config.algorithm_type == "dpmsolver++":
-            # See https://arxiv.org/abs/2211.01095 for detailed derivations
+            # See https://huggingface.co/papers/2211.01095 for detailed derivations
             if self.config.solver_type == "midpoint":
                 x_t = (
                     (sigma_t / sigma_s0) * sample
@@ -404,7 +406,7 @@ class FlaxDPMSolverMultistepScheduler(FlaxSchedulerMixin, ConfigMixin):
                     + (alpha_t * ((jnp.exp(-h) - 1.0) / h + 1.0)) * D1
                 )
         elif self.config.algorithm_type == "dpmsolver":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
+            # See https://huggingface.co/papers/2206.00927 for detailed derivations
             if self.config.solver_type == "midpoint":
                 x_t = (
                     (alpha_t / alpha_s0) * sample
@@ -458,7 +460,7 @@ class FlaxDPMSolverMultistepScheduler(FlaxSchedulerMixin, ConfigMixin):
         D1 = D1_0 + (r0 / (r0 + r1)) * (D1_0 - D1_1)
         D2 = (1.0 / (r0 + r1)) * (D1_0 - D1_1)
         if self.config.algorithm_type == "dpmsolver++":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
+            # See https://huggingface.co/papers/2206.00927 for detailed derivations
             x_t = (
                 (sigma_t / sigma_s0) * sample
                 - (alpha_t * (jnp.exp(-h) - 1.0)) * D0
@@ -466,7 +468,7 @@ class FlaxDPMSolverMultistepScheduler(FlaxSchedulerMixin, ConfigMixin):
                 - (alpha_t * ((jnp.exp(-h) - 1.0 + h) / h**2 - 0.5)) * D2
             )
         elif self.config.algorithm_type == "dpmsolver":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
+            # See https://huggingface.co/papers/2206.00927 for detailed derivations
             x_t = (
                 (alpha_t / alpha_s0) * sample
                 - (sigma_t * (jnp.exp(h) - 1.0)) * D0

diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py

@@ -1,4 +1,4 @@
-# Copyright 2024 TSAIL Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 TSAIL Team and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -257,7 +257,7 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
         clipped_idx = torch.searchsorted(torch.flip(self.lambda_t, [0]), self.config.lambda_min_clipped).item()
         self.noisiest_timestep = self.config.num_train_timesteps - 1 - clipped_idx
 
-        # "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.noisiest_timestep, num_inference_steps + 1).round()[:-1].copy().astype(np.int64)
@@ -338,7 +338,7 @@ class DPMSolverMultistepInverseScheduler(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
@@ -513,7 +513,7 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 1:
                 sample = args[1]
             else:
-                raise ValueError("missing `sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep is not None:
             deprecate(
                 "timesteps",
@@ -609,7 +609,7 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 2:
                 sample = args[2]
             else:
-                raise ValueError(" missing `sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep is not None:
             deprecate(
                 "timesteps",
@@ -679,7 +679,7 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 2:
                 sample = args[2]
             else:
-                raise ValueError(" missing `sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep_list is not None:
             deprecate(
                 "timestep_list",
@@ -714,7 +714,7 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
         r0 = h_0 / h
         D0, D1 = m0, (1.0 / r0) * (m0 - m1)
         if self.config.algorithm_type == "dpmsolver++":
-            # See https://arxiv.org/abs/2211.01095 for detailed derivations
+            # See https://huggingface.co/papers/2211.01095 for detailed derivations
             if self.config.solver_type == "midpoint":
                 x_t = (
                     (sigma_t / sigma_s0) * sample
@@ -728,7 +728,7 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
                     + (alpha_t * ((torch.exp(-h) - 1.0) / h + 1.0)) * D1
                 )
         elif self.config.algorithm_type == "dpmsolver":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
+            # See https://huggingface.co/papers/2206.00927 for detailed derivations
             if self.config.solver_type == "midpoint":
                 x_t = (
                     (alpha_t / alpha_s0) * sample
@@ -804,7 +804,7 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 2:
                 sample = args[2]
             else:
-                raise ValueError(" missing`sample` as a required keyward argument")
+                raise ValueError("missing `sample` as a required keyword argument")
         if timestep_list is not None:
             deprecate(
                 "timestep_list",
@@ -845,7 +845,7 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
         D1 = D1_0 + (r0 / (r0 + r1)) * (D1_0 - D1_1)
         D2 = (1.0 / (r0 + r1)) * (D1_0 - D1_1)
         if self.config.algorithm_type == "dpmsolver++":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
+            # See https://huggingface.co/papers/2206.00927 for detailed derivations
             x_t = (
                 (sigma_t / sigma_s0) * sample
                 - (alpha_t * (torch.exp(-h) - 1.0)) * D0
@@ -853,7 +853,7 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
                 - (alpha_t * ((torch.exp(-h) - 1.0 + h) / h**2 - 0.5)) * D2
             )
         elif self.config.algorithm_type == "dpmsolver":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
+            # See https://huggingface.co/papers/2206.00927 for detailed derivations
             x_t = (
                 (alpha_t / alpha_s0) * sample
                 - (sigma_t * (torch.exp(h) - 1.0)) * D0