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

diffusers/schedulers/scheduling_lms_discrete.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Katherine Crowson and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Katherine Crowson 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.
@@ -272,7 +272,7 @@ class LMSDiscreteScheduler(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, dtype=np.float32)[
                 ::-1

diffusers/schedulers/scheduling_lms_discrete_flax.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Katherine Crowson and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Katherine Crowson 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.

diffusers/schedulers/scheduling_pndm.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Zhejiang University Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Zhejiang University 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.
@@ -146,7 +146,7 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
         self.init_noise_sigma = 1.0
 
         # For now we only support F-PNDM, i.e. the runge-kutta method
-        # For more information on the algorithm please take a look at the paper: https://arxiv.org/pdf/2202.09778.pdf
+        # For more information on the algorithm please take a look at the paper: https://huggingface.co/papers/2202.09778
         # mainly at formula (9), (12), (13) and the Algorithm 2.
         self.pndm_order = 4
 
@@ -175,7 +175,7 @@ class PNDMScheduler(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":
             self._timesteps = (
                 np.linspace(0, self.config.num_train_timesteps - 1, num_inference_steps).round().astype(np.int64)
@@ -403,7 +403,7 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
         return sample
 
     def _get_prev_sample(self, sample, timestep, prev_timestep, model_output):
-        # See formula (9) of PNDM paper https://arxiv.org/pdf/2202.09778.pdf
+        # See formula (9) of PNDM paper https://huggingface.co/papers/2202.09778
         # this function computes x_(t−δ) using the formula of (9)
         # Note that x_t needs to be added to both sides of the equation
 

diffusers/schedulers/scheduling_pndm_flax.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Zhejiang University Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Zhejiang University 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.
@@ -80,7 +80,7 @@ class FlaxPNDMScheduler(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/2202.09778
+    For more details, see the original paper: https://huggingface.co/papers/2202.09778
 
     Args:
         num_train_timesteps (`int`): number of diffusion steps used to train the model.
@@ -134,7 +134,7 @@ class FlaxPNDMScheduler(FlaxSchedulerMixin, ConfigMixin):
         self.dtype = dtype
 
         # For now we only support F-PNDM, i.e. the runge-kutta method
-        # For more information on the algorithm please take a look at the paper: https://arxiv.org/pdf/2202.09778.pdf
+        # For more information on the algorithm please take a look at the paper: https://huggingface.co/papers/2202.09778
         # mainly at formula (9), (12), (13) and the Algorithm 2.
         self.pndm_order = 4
 
@@ -452,7 +452,7 @@ class FlaxPNDMScheduler(FlaxSchedulerMixin, ConfigMixin):
         return (prev_sample, state)
 
     def _get_prev_sample(self, state: PNDMSchedulerState, sample, timestep, prev_timestep, model_output):
-        # See formula (9) of PNDM paper https://arxiv.org/pdf/2202.09778.pdf
+        # See formula (9) of PNDM paper https://huggingface.co/papers/2202.09778
         # this function computes x_(t−δ) using the formula of (9)
         # Note that x_t needs to be added to both sides of the equation
 

diffusers/schedulers/scheduling_repaint.py

@@ -1,4 +1,4 @@
-# Copyright 2024 ETH Zurich Computer Vision Lab and The HuggingFace Team. All rights reserved.
+# Copyright 2025 ETH Zurich Computer Vision 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.
@@ -233,10 +233,10 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
         beta_prod_t_prev = 1 - alpha_prod_t_prev
 
         # For t > 0, compute predicted variance βt (see formula (6) and (7) from
-        # https://arxiv.org/pdf/2006.11239.pdf) and sample from it to get
+        # 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
-        # Is equivalent to formula (16) in https://arxiv.org/pdf/2010.02502.pdf
+        # Is equivalent to formula (16) in https://huggingface.co/papers/2010.02502
         # without eta.
         # variance = (1 - alpha_prod_t_prev) / (1 - alpha_prod_t) * self.betas[t]
         variance = (beta_prod_t_prev / beta_prod_t) * (1 - alpha_prod_t / alpha_prod_t_prev)
@@ -288,7 +288,7 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
         beta_prod_t = 1 - alpha_prod_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
         pred_original_sample = (sample - beta_prod_t**0.5 * model_output) / alpha_prod_t**0.5
 
         # 3. Clip "predicted x_0"
@@ -312,20 +312,20 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
             variance = std_dev_t * noise
 
         # 6. compute "direction pointing to x_t" of formula (12)
-        # from https://arxiv.org/pdf/2010.02502.pdf
+        # from https://huggingface.co/papers/2010.02502
         pred_sample_direction = (1 - alpha_prod_t_prev - std_dev_t**2) ** 0.5 * model_output
 
-        # 7. compute x_{t-1} of formula (12) from https://arxiv.org/pdf/2010.02502.pdf
+        # 7. compute x_{t-1} of formula (12) from https://huggingface.co/papers/2010.02502
         prev_unknown_part = alpha_prod_t_prev**0.5 * pred_original_sample + pred_sample_direction + variance
 
-        # 8. Algorithm 1 Line 5 https://arxiv.org/pdf/2201.09865.pdf
+        # 8. Algorithm 1 Line 5 https://huggingface.co/papers/2201.09865
         # The computation reported in Algorithm 1 Line 5 is incorrect. Line 5 refers to formula (8a) of the same paper,
         # which tells to sample from a Gaussian distribution with mean "(alpha_prod_t_prev**0.5) * original_image"
         # and variance "(1 - alpha_prod_t_prev)". This means that the standard Gaussian distribution "noise" should be
         # scaled by the square root of the variance (as it is done here), however Algorithm 1 Line 5 tells to scale by the variance.
         prev_known_part = (alpha_prod_t_prev**0.5) * original_image + ((1 - alpha_prod_t_prev) ** 0.5) * noise
 
-        # 9. Algorithm 1 Line 8 https://arxiv.org/pdf/2201.09865.pdf
+        # 9. Algorithm 1 Line 8 https://huggingface.co/papers/2201.09865
         pred_prev_sample = mask * prev_known_part + (1.0 - mask) * prev_unknown_part
 
         if not return_dict:
@@ -348,7 +348,7 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
             else:
                 noise = randn_tensor(sample.shape, generator=generator, device=sample.device, dtype=sample.dtype)
 
-            # 10. Algorithm 1 Line 10 https://arxiv.org/pdf/2201.09865.pdf
+            # 10. Algorithm 1 Line 10 https://huggingface.co/papers/2201.09865
             sample = (1 - beta) ** 0.5 * sample + beta**0.5 * noise
 
         return sample

diffusers/schedulers/scheduling_sasolver.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Shuchen Xue, etc. in University of Chinese Academy of Sciences Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Shuchen Xue, etc. in University of Chinese Academy of Sciences 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.
@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# DISCLAIMER: check https://arxiv.org/abs/2309.05019
+# DISCLAIMER: check https://huggingface.co/papers/2309.05019
 # The codebase is modified based on https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py
 
 import math
@@ -109,7 +109,7 @@ class SASolverScheduler(SchedulerMixin, ConfigMixin):
             Stochasticity during the sampling. Default in init is `lambda t: 1 if t >= 200 and t <= 800 else 0`.
             SA-Solver will sample from vanilla diffusion ODE if tau_func is set to `lambda t: 0`. SA-Solver will sample
             from vanilla diffusion SDE if tau_func is set to `lambda t: 1`. For more details, please check
-            https://arxiv.org/abs/2309.05019
+            https://huggingface.co/papers/2309.05019
         thresholding (`bool`, defaults to `False`):
             Whether to use the "dynamic thresholding" method. This is unsuitable for latent-space diffusion models such
             as Stable Diffusion.
@@ -273,7 +273,7 @@ class SASolverScheduler(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).round()[::-1][:-1].copy().astype(np.int64)
@@ -348,7 +348,7 @@ class SASolverScheduler(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
@@ -522,7 +522,7 @@ class SASolverScheduler(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",
@@ -812,22 +812,22 @@ class SASolverScheduler(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 noise is None:
             if len(args) > 2:
                 noise = args[2]
             else:
-                raise ValueError(" missing `noise` as a required keyward argument")
+                raise ValueError("missing `noise` as a required keyword argument")
         if order is None:
             if len(args) > 3:
                 order = args[3]
             else:
-                raise ValueError(" missing `order` as a required keyward argument")
+                raise ValueError("missing `order` as a required keyword argument")
         if tau is None:
             if len(args) > 4:
                 tau = args[4]
             else:
-                raise ValueError(" missing `tau` as a required keyward argument")
+                raise ValueError("missing `tau` as a required keyword argument")
         if prev_timestep is not None:
             deprecate(
                 "prev_timestep",
@@ -943,27 +943,27 @@ class SASolverScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 1:
                 last_sample = args[1]
             else:
-                raise ValueError(" missing`last_sample` as a required keyward argument")
+                raise ValueError("missing `last_sample` as a required keyword argument")
         if last_noise is None:
             if len(args) > 2:
                 last_noise = args[2]
             else:
-                raise ValueError(" missing`last_noise` as a required keyward argument")
+                raise ValueError("missing `last_noise` as a required keyword argument")
         if this_sample is None:
             if len(args) > 3:
                 this_sample = args[3]
             else:
-                raise ValueError(" missing`this_sample` as a required keyward argument")
+                raise ValueError("missing `this_sample` as a required keyword argument")
         if order is None:
             if len(args) > 4:
                 order = args[4]
             else:
-                raise ValueError(" missing`order` as a required keyward argument")
+                raise ValueError("missing `order` as a required keyword argument")
         if tau is None:
             if len(args) > 5:
                 tau = args[5]
             else:
-                raise ValueError(" missing`tau` as a required keyward argument")
+                raise ValueError("missing `tau` as a required keyword argument")
         if this_timestep is not None:
             deprecate(
                 "this_timestep",

diffusers/schedulers/scheduling_scm.py

@@ -1,4 +1,4 @@
-# # Copyright 2024 Sana-Sprint Authors and The HuggingFace Team. All rights reserved.
+# # Copyright 2025 Sana-Sprint 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.

diffusers/schedulers/scheduling_sde_ve.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Google Brain and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Google Brain 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.

diffusers/schedulers/scheduling_sde_ve_flax.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Google Brain and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Google Brain 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 FlaxScoreSdeVeScheduler(FlaxSchedulerMixin, ConfigMixin):
     """
     The variance exploding stochastic differential equation (SDE) scheduler.
 
-    For more information, see the original paper: https://arxiv.org/abs/2011.13456
+    For more information, see the original paper: https://huggingface.co/papers/2011.13456
 
     [`~ConfigMixin`] takes care of storing all config attributes that are passed in the scheduler's `__init__`
     function, such as `num_train_timesteps`. They can be accessed via `scheduler.config.num_train_timesteps`.

diffusers/schedulers/scheduling_tcd.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Stanford University Team and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Stanford University 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.
@@ -96,7 +96,7 @@ def betas_for_alpha_bar(
 # Copied from diffusers.schedulers.scheduling_ddim.rescale_zero_terminal_snr
 def rescale_zero_terminal_snr(betas: torch.Tensor) -> torch.Tensor:
     """
-    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:
@@ -334,7 +334,7 @@ class TCDScheduler(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

diffusers/schedulers/scheduling_unclip.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Kakao Brain and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Kakao Brain 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.
@@ -191,7 +191,7 @@ class UnCLIPScheduler(SchedulerMixin, ConfigMixin):
         else:
             beta = 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 = beta_prod_t_prev / beta_prod_t * beta
@@ -266,7 +266,7 @@ class UnCLIPScheduler(SchedulerMixin, ConfigMixin):
             alpha = 1 - beta
 
         # 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":
@@ -284,12 +284,12 @@ class UnCLIPScheduler(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) * beta) / beta_prod_t
         current_sample_coeff = alpha ** (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_unipc_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.
@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# DISCLAIMER: check https://arxiv.org/abs/2302.04867 and https://github.com/wl-zhao/UniPC for more info
+# DISCLAIMER: check https://huggingface.co/papers/2302.04867 and https://github.com/wl-zhao/UniPC 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
@@ -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:
@@ -308,7 +308,7 @@ class UniPCMultistepScheduler(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)
@@ -429,7 +429,7 @@ class UniPCMultistepScheduler(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
@@ -596,7 +596,7 @@ class UniPCMultistepScheduler(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",
@@ -672,12 +672,12 @@ class UniPCMultistepScheduler(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 order is None:
             if len(args) > 2:
                 order = args[2]
             else:
-                raise ValueError(" missing `order` as a required keyward argument")
+                raise ValueError("missing `order` as a required keyword argument")
         if prev_timestep is not None:
             deprecate(
                 "prev_timestep",
@@ -804,17 +804,17 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
             if len(args) > 1:
                 last_sample = args[1]
             else:
-                raise ValueError(" missing`last_sample` as a required keyward argument")
+                raise ValueError("missing `last_sample` as a required keyword argument")
         if this_sample is None:
             if len(args) > 2:
                 this_sample = args[2]
             else:
-                raise ValueError(" missing`this_sample` as a required keyward argument")
+                raise ValueError("missing `this_sample` as a required keyword argument")
         if order is None:
             if len(args) > 3:
                 order = args[3]
             else:
-                raise ValueError(" missing`order` as a required keyward argument")
+                raise ValueError("missing `order` as a required keyword argument")
         if this_timestep is not None:
             deprecate(
                 "this_timestep",

diffusers/schedulers/scheduling_utils.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 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.

diffusers/schedulers/scheduling_utils_flax.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 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.

diffusers/schedulers/scheduling_vq_diffusion.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Microsoft and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Microsoft 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.

diffusers/training_utils.py

@@ -149,9 +149,9 @@ def compute_dream_and_update_latents(
     dream_detail_preservation: float = 1.0,
 ) -> Tuple[Optional[torch.Tensor], Optional[torch.Tensor]]:
     """
-    Implements "DREAM (Diffusion Rectification and Estimation-Adaptive Models)" from http://arxiv.org/abs/2312.00210.
-    DREAM helps align training with sampling to help training be more efficient and accurate at the cost of an extra
-    forward step without gradients.
+    Implements "DREAM (Diffusion Rectification and Estimation-Adaptive Models)" from
+    https://huggingface.co/papers/2312.00210. DREAM helps align training with sampling to help training be more
+    efficient and accurate at the cost of an extra forward step without gradients.
 
     Args:
         `unet`: The state unet to use to make a prediction.
@@ -247,6 +247,14 @@ def _set_state_dict_into_text_encoder(
     set_peft_model_state_dict(text_encoder, text_encoder_state_dict, adapter_name="default")
 
 
+def _collate_lora_metadata(modules_to_save: Dict[str, torch.nn.Module]) -> Dict[str, Any]:
+    metadatas = {}
+    for module_name, module in modules_to_save.items():
+        if module is not None:
+            metadatas[f"{module_name}_lora_adapter_metadata"] = module.peft_config["default"].to_dict()
+    return metadatas
+
+
 def compute_density_for_timestep_sampling(
     weighting_scheme: str,
     batch_size: int,
@@ -261,7 +269,7 @@ def compute_density_for_timestep_sampling(
 
     Courtesy: This was contributed by Rafie Walker in https://github.com/huggingface/diffusers/pull/8528.
 
-    SD3 paper reference: https://arxiv.org/abs/2403.03206v1.
+    SD3 paper reference: https://huggingface.co/papers/2403.03206v1.
     """
     if weighting_scheme == "logit_normal":
         u = torch.normal(mean=logit_mean, std=logit_std, size=(batch_size,), device=device, generator=generator)
@@ -280,7 +288,7 @@ def compute_loss_weighting_for_sd3(weighting_scheme: str, sigmas=None):
 
     Courtesy: This was contributed by Rafie Walker in https://github.com/huggingface/diffusers/pull/8528.
 
-    SD3 paper reference: https://arxiv.org/abs/2403.03206v1.
+    SD3 paper reference: https://huggingface.co/papers/2403.03206v1.
     """
     if weighting_scheme == "sigma_sqrt":
         weighting = (sigmas**-2.0).float()

diffusers/utils/__init__.py

@@ -62,21 +62,25 @@ from .import_utils import (
     get_objects_from_module,
     is_accelerate_available,
     is_accelerate_version,
+    is_better_profanity_available,
     is_bitsandbytes_available,
     is_bitsandbytes_version,
     is_bs4_available,
+    is_cosmos_guardrail_available,
     is_flax_available,
     is_ftfy_available,
     is_gguf_available,
     is_gguf_version,
     is_google_colab,
     is_hf_hub_version,
+    is_hpu_available,
     is_inflect_available,
     is_invisible_watermark_available,
     is_k_diffusion_available,
     is_k_diffusion_version,
     is_librosa_available,
     is_matplotlib_available,
+    is_nltk_available,
     is_note_seq_available,
     is_onnx_available,
     is_opencv_available,
@@ -84,6 +88,7 @@ from .import_utils import (
     is_optimum_quanto_version,
     is_peft_available,
     is_peft_version,
+    is_pytorch_retinaface_available,
     is_safetensors_available,
     is_scipy_available,
     is_sentencepiece_available,

diffusers/utils/accelerate_utils.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 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.

diffusers/utils/doc_utils.py

@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Team. All rights reserved.
+# Copyright 2025 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.