[docs] Clean scheduler api (#4204)

* clean scheduler mixin

* up to dpmsolvermultistep

* finish cleaning

* first draft

* fix overview table

* apply feedback

* update reference code

src/diffusers/schedulers/scheduling_k_dpm_2_ancestral_discrete.py

@@ -71,36 +71,35 @@ def betas_for_alpha_bar(
 
 class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
     """
-    Scheduler created by @crowsonkb in [k_diffusion](https://github.com/crowsonkb/k-diffusion), see:
-    https://github.com/crowsonkb/k-diffusion/blob/5b3af030dd83e0297272d861c19477735d0317ec/k_diffusion/sampling.py#L188
+    KDPM2DiscreteScheduler with ancestral sampling is inspired by the DPMSolver2 and Algorithm 2 from the [Elucidating
+    the Design Space of Diffusion-Based Generative Models](https://huggingface.co/papers/2206.00364) paper.
 
-    Scheduler inspired by DPM-Solver-2 and Algorthim 2 from Karras et al. (2022).
-
-    [`~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`.
-    [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and
-    [`~SchedulerMixin.from_pretrained`] functions.
+    This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
+    methods the library implements for all schedulers such as loading and saving.
 
     Args:
-        num_train_timesteps (`int`): number of diffusion steps used to train the model. beta_start (`float`): the
-        starting `beta` value of inference. beta_end (`float`): the final `beta` value. beta_schedule (`str`):
-            the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
+        num_train_timesteps (`int`, defaults to 1000):
+            The number of diffusion steps to train the model.
+        beta_start (`float`, defaults to 0.00085):
+            The starting `beta` value of inference.
+        beta_end (`float`, defaults to 0.012):
+            The final `beta` value.
+        beta_schedule (`str`, defaults to `"linear"`):
+            The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
             `linear` or `scaled_linear`.
-        trained_betas (`np.ndarray`, optional):
-            option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
-            options to clip the variance used when adding noise to the denoised sample. Choose from `fixed_small`,
-            `fixed_small_log`, `fixed_large`, `fixed_large_log`, `learned` or `learned_range`.
-        prediction_type (`str`, default `epsilon`, optional):
-            prediction type of the scheduler function, one of `epsilon` (predicting the noise of the diffusion
-            process), `sample` (directly predicting the noisy sample`) or `v_prediction` (see section 2.4
-            https://imagen.research.google/video/paper.pdf)
-        timestep_spacing (`str`, default `"linspace"`):
-            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_offset (`int`, default `0`):
-            an offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False`, to make the last step use step 0 for the previous alpha product, as done in
-            stable diffusion.
+        trained_betas (`np.ndarray`, *optional*):
+            Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`.
+        prediction_type (`str`, defaults to `epsilon`, *optional*):
+            Prediction type of the scheduler function; can be `epsilon` (predicts the noise of the diffusion process),
+            `sample` (directly predicts the noisy sample`) or `v_prediction` (see section 2.4 of [Imagen
+            Video](https://imagen.research.google/video/paper.pdf) paper).
+        timestep_spacing (`str`, defaults to `"linspace"`):
+            The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
+            Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
+        steps_offset (`int`, defaults to 0):
+            An offset added to the inference steps. You can use a combination of `offset=1` and
+            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
+            Diffusion.
     """
 
     _compatibles = [e.name for e in KarrasDiffusionSchedulers]
@@ -172,12 +171,18 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
         timestep: Union[float, torch.FloatTensor],
     ) -> torch.FloatTensor:
         """
-        Args:
         Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
         current timestep.
-            sample (`torch.FloatTensor`): input sample timestep (`int`, optional): current timestep
+
+        Args:
+            sample (`torch.FloatTensor`):
+                The input sample.
+            timestep (`int`, *optional*):
+                The current timestep in the diffusion chain.
+
         Returns:
-            `torch.FloatTensor`: scaled input sample
+            `torch.FloatTensor`:
+                A scaled input sample.
         """
         step_index = self.index_for_timestep(timestep)
 
@@ -196,13 +201,13 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
         num_train_timesteps: Optional[int] = None,
     ):
         """
-        Sets the timesteps used for the diffusion chain. Supporting function to be run before inference.
+        Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
         Args:
             num_inference_steps (`int`):
-                the number of diffusion steps used when generating samples with a pre-trained model.
-            device (`str` or `torch.device`, optional):
-                the device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
+                The number of diffusion steps used when generating samples with a pre-trained model.
+            device (`str` or `torch.device`, *optional*):
+                The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
         """
         self.num_inference_steps = num_inference_steps
 
@@ -307,17 +312,25 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
-        Args:
-        Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
         process from the learned model outputs (most often the predicted noise).
-            model_output (`torch.FloatTensor` or `np.ndarray`): direct output from learned diffusion model. timestep
-            (`int`): current discrete timestep in the diffusion chain. sample (`torch.FloatTensor` or `np.ndarray`):
-                current instance of sample being created by diffusion process.
-            return_dict (`bool`): option for returning tuple rather than SchedulerOutput class
+
+        Args:
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
+            timestep (`float`):
+                The current discrete timestep in the diffusion chain.
+            sample (`torch.FloatTensor`):
+                A current instance of a sample created by the diffusion process.
+            generator (`torch.Generator`, *optional*):
+                A random number generator.
+            return_dict (`bool`):
+                Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or tuple.
+
         Returns:
             [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`:
-            [`~schedulers.scheduling_utils.SchedulerOutput`] if `return_dict` is True, otherwise a `tuple`. When
-            returning a tuple, the first element is the sample tensor.
+                If return_dict is `True`, [`~schedulers.scheduling_ddim.SchedulerOutput`] is returned, otherwise a
+                tuple is returned where the first element is the sample tensor.
         """
         step_index = self.index_for_timestep(timestep)
 

src/diffusers/schedulers/scheduling_k_dpm_2_discrete.py

@@ -70,36 +70,35 @@ def betas_for_alpha_bar(
 
 class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
     """
-    Scheduler created by @crowsonkb in [k_diffusion](https://github.com/crowsonkb/k-diffusion), see:
-    https://github.com/crowsonkb/k-diffusion/blob/5b3af030dd83e0297272d861c19477735d0317ec/k_diffusion/sampling.py#L188
+    KDPM2DiscreteScheduler is inspired by the DPMSolver2 and Algorithm 2 from the [Elucidating the Design Space of
+    Diffusion-Based Generative Models](https://huggingface.co/papers/2206.00364) paper.
 
-    Scheduler inspired by DPM-Solver-2 and Algorthim 2 from Karras et al. (2022).
-
-    [`~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`.
-    [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and
-    [`~SchedulerMixin.from_pretrained`] functions.
+    This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
+    methods the library implements for all schedulers such as loading and saving.
 
     Args:
-        num_train_timesteps (`int`): number of diffusion steps used to train the model. beta_start (`float`): the
-        starting `beta` value of inference. beta_end (`float`): the final `beta` value. beta_schedule (`str`):
-            the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
+        num_train_timesteps (`int`, defaults to 1000):
+            The number of diffusion steps to train the model.
+        beta_start (`float`, defaults to 0.00085):
+            The starting `beta` value of inference.
+        beta_end (`float`, defaults to 0.012):
+            The final `beta` value.
+        beta_schedule (`str`, defaults to `"linear"`):
+            The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
             `linear` or `scaled_linear`.
-        trained_betas (`np.ndarray`, optional):
-            option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
-            options to clip the variance used when adding noise to the denoised sample. Choose from `fixed_small`,
-            `fixed_small_log`, `fixed_large`, `fixed_large_log`, `learned` or `learned_range`.
-        prediction_type (`str`, default `epsilon`, optional):
-            prediction type of the scheduler function, one of `epsilon` (predicting the noise of the diffusion
-            process), `sample` (directly predicting the noisy sample`) or `v_prediction` (see section 2.4
-            https://imagen.research.google/video/paper.pdf)
-        timestep_spacing (`str`, default `"linspace"`):
-            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_offset (`int`, default `0`):
-            an offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False`, to make the last step use step 0 for the previous alpha product, as done in
-            stable diffusion.
+        trained_betas (`np.ndarray`, *optional*):
+            Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`.
+        prediction_type (`str`, defaults to `epsilon`, *optional*):
+            Prediction type of the scheduler function; can be `epsilon` (predicts the noise of the diffusion process),
+            `sample` (directly predicts the noisy sample`) or `v_prediction` (see section 2.4 of [Imagen
+            Video](https://imagen.research.google/video/paper.pdf) paper).
+        timestep_spacing (`str`, defaults to `"linspace"`):
+            The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
+            Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
+        steps_offset (`int`, defaults to 0):
+            An offset added to the inference steps. You can use a combination of `offset=1` and
+            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
+            Diffusion.
     """
 
     _compatibles = [e.name for e in KarrasDiffusionSchedulers]
@@ -171,12 +170,18 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
         timestep: Union[float, torch.FloatTensor],
     ) -> torch.FloatTensor:
         """
-        Args:
         Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
         current timestep.
-            sample (`torch.FloatTensor`): input sample timestep (`int`, optional): current timestep
+
+        Args:
+            sample (`torch.FloatTensor`):
+                The input sample.
+            timestep (`int`, *optional*):
+                The current timestep in the diffusion chain.
+
         Returns:
-            `torch.FloatTensor`: scaled input sample
+            `torch.FloatTensor`:
+                A scaled input sample.
         """
         step_index = self.index_for_timestep(timestep)
 
@@ -195,13 +200,13 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
         num_train_timesteps: Optional[int] = None,
     ):
         """
-        Sets the timesteps used for the diffusion chain. Supporting function to be run before inference.
+        Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
         Args:
             num_inference_steps (`int`):
-                the number of diffusion steps used when generating samples with a pre-trained model.
-            device (`str` or `torch.device`, optional):
-                the device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
+                The number of diffusion steps used when generating samples with a pre-trained model.
+            device (`str` or `torch.device`, *optional*):
+                The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
         """
         self.num_inference_steps = num_inference_steps
 
@@ -295,17 +300,23 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
-        Args:
-        Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
         process from the learned model outputs (most often the predicted noise).
-            model_output (`torch.FloatTensor` or `np.ndarray`): direct output from learned diffusion model. timestep
-            (`int`): current discrete timestep in the diffusion chain. sample (`torch.FloatTensor` or `np.ndarray`):
-                current instance of sample being created by diffusion process.
-            return_dict (`bool`): option for returning tuple rather than SchedulerOutput class
+
+        Args:
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
+            timestep (`float`):
+                The current discrete timestep in the diffusion chain.
+            sample (`torch.FloatTensor`):
+                A current instance of a sample created by the diffusion process.
+            return_dict (`bool`):
+                Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or tuple.
+
         Returns:
             [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`:
-            [`~schedulers.scheduling_utils.SchedulerOutput`] if `return_dict` is True, otherwise a `tuple`. When
-            returning a tuple, the first element is the sample tensor.
+                If return_dict is `True`, [`~schedulers.scheduling_utils.SchedulerOutput`] is returned, otherwise a
+                tuple is returned where the first element is the sample tensor.
         """
         step_index = self.index_for_timestep(timestep)
 

src/diffusers/schedulers/scheduling_karras_ve.py

@@ -47,34 +47,32 @@ class KarrasVeOutput(BaseOutput):
 
 class KarrasVeScheduler(SchedulerMixin, ConfigMixin):
     """
-    Stochastic sampling from Karras et al. [1] tailored to the Variance-Expanding (VE) models [2]. Use Algorithm 2 and
-    the VE column of Table 1 from [1] for reference.
+    A stochastic scheduler tailored to variance-expanding models.
 
-    [1] Karras, Tero, et al. "Elucidating the Design Space of Diffusion-Based Generative Models."
-    https://arxiv.org/abs/2206.00364 [2] Song, Yang, et al. "Score-based generative modeling through stochastic
-    differential equations." https://arxiv.org/abs/2011.13456
+    This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
+    methods the library implements for all schedulers such as loading and saving.
 
-    [`~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`.
-    [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and
-    [`~SchedulerMixin.from_pretrained`] functions.
+    <Tip>
 
-    For more details on the parameters, see the original paper's Appendix E.: "Elucidating the Design Space of
-    Diffusion-Based Generative Models." https://arxiv.org/abs/2206.00364. The grid search values used to find the
-    optimal {s_noise, s_churn, s_min, s_max} for a specific model are described in Table 5 of the paper.
+    For more details on the parameters, see [Appendix E](https://arxiv.org/abs/2206.00364). The grid search values used
+    to find the optimal `{s_noise, s_churn, s_min, s_max}` for a specific model are described in Table 5 of the paper.
 
-    Args:
-        sigma_min (`float`): minimum noise magnitude
-        sigma_max (`float`): maximum noise magnitude
-        s_noise (`float`): the amount of additional noise to counteract loss of detail during sampling.
-            A reasonable range is [1.000, 1.011].
-        s_churn (`float`): the parameter controlling the overall amount of stochasticity.
-            A reasonable range is [0, 100].
-        s_min (`float`): the start value of the sigma range where we add noise (enable stochasticity).
-            A reasonable range is [0, 10].
-        s_max (`float`): the end value of the sigma range where we add noise.
-            A reasonable range is [0.2, 80].
+    </Tip>
 
+    Args:
+        sigma_min (`float`, defaults to 0.02):
+            The minimum noise magnitude.
+        sigma_max (`float`, defaults to 100):
+            The maximum noise magnitude.
+        s_noise (`float`, defaults to 1.007):
+            The amount of additional noise to counteract loss of detail during sampling. A reasonable range is [1.000,
+            1.011].
+        s_churn (`float`, defaults to 80):
+            The parameter controlling the overall amount of stochasticity. A reasonable range is [0, 100].
+        s_min (`float`, defaults to 0.05):
+            The start value of the sigma range to add noise (enable stochasticity). A reasonable range is [0, 10].
+        s_max (`float`, defaults to 50):
+            The end value of the sigma range to add noise. A reasonable range is [0.2, 80].
     """
 
     order = 2
@@ -103,22 +101,26 @@ class KarrasVeScheduler(SchedulerMixin, ConfigMixin):
         current timestep.
 
         Args:
-            sample (`torch.FloatTensor`): input sample
-            timestep (`int`, optional): current timestep
+            sample (`torch.FloatTensor`):
+                The input sample.
+            timestep (`int`, *optional*):
+                The current timestep in the diffusion chain.
 
         Returns:
-            `torch.FloatTensor`: scaled input sample
+            `torch.FloatTensor`:
+                A scaled input sample.
         """
         return sample
 
     def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None):
         """
-        Sets the continuous timesteps used for the diffusion chain. Supporting function to be run before inference.
+        Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
         Args:
             num_inference_steps (`int`):
-                the number of diffusion steps used when generating samples with a pre-trained model.
-
+                The number of diffusion steps used when generating samples with a pre-trained model.
+            device (`str` or `torch.device`, *optional*):
+                The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
         """
         self.num_inference_steps = num_inference_steps
         timesteps = np.arange(0, self.num_inference_steps)[::-1].copy()
@@ -136,10 +138,15 @@ class KarrasVeScheduler(SchedulerMixin, ConfigMixin):
         self, sample: torch.FloatTensor, sigma: float, generator: Optional[torch.Generator] = None
     ) -> Tuple[torch.FloatTensor, float]:
         """
-        Explicit Langevin-like "churn" step of adding noise to the sample according to a factor gamma_i ≥ 0 to reach a
-        higher noise level sigma_hat = sigma_i + gamma_i*sigma_i.
+        Explicit Langevin-like "churn" step of adding noise to the sample according to a `gamma_i ≥ 0` to reach a
+        higher noise level `sigma_hat = sigma_i + gamma_i*sigma_i`.
 
-        TODO Args:
+        Args:
+            sample (`torch.FloatTensor`):
+                The input sample.
+            sigma (`float`):
+            generator (`torch.Generator`, *optional*):
+                A random number generator.
         """
         if self.config.s_min <= sigma <= self.config.s_max:
             gamma = min(self.config.s_churn / self.num_inference_steps, 2**0.5 - 1)
@@ -162,21 +169,22 @@ class KarrasVeScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[KarrasVeOutput, Tuple]:
         """
-        Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
         process from the learned model outputs (most often the predicted noise).
 
         Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
-            sigma_hat (`float`): TODO
-            sigma_prev (`float`): TODO
-            sample_hat (`torch.FloatTensor`): TODO
-            return_dict (`bool`): option for returning tuple rather than KarrasVeOutput class
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
+            sigma_hat (`float`):
+            sigma_prev (`float`):
+            sample_hat (`torch.FloatTensor`):
+            return_dict (`bool`, *optional*, defaults to `True`):
+                Whether or not to return a [`~schedulers.scheduling_karras_ve.KarrasVESchedulerOutput`] or `tuple`.
 
-            KarrasVeOutput: updated sample in the diffusion chain and derivative (TODO double check).
         Returns:
-            [`~schedulers.scheduling_karras_ve.KarrasVeOutput`] or `tuple`:
-            [`~schedulers.scheduling_karras_ve.KarrasVeOutput`] if `return_dict` is True, otherwise a `tuple`. When
-            returning a tuple, the first element is the sample tensor.
+            [`~schedulers.scheduling_karras_ve.KarrasVESchedulerOutput`] or `tuple`:
+                If return_dict is `True`, [`~schedulers.scheduling_karras_ve.KarrasVESchedulerOutput`] is returned,
+                otherwise a tuple is returned where the first element is the sample tensor.
 
         """
 
@@ -202,16 +210,18 @@ class KarrasVeScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[KarrasVeOutput, Tuple]:
         """
-        Correct the predicted sample based on the output model_output of the network. TODO complete description
+        Corrects the predicted sample based on the `model_output` of the network.
 
         Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
             sigma_hat (`float`): TODO
             sigma_prev (`float`): TODO
             sample_hat (`torch.FloatTensor`): TODO
             sample_prev (`torch.FloatTensor`): TODO
             derivative (`torch.FloatTensor`): TODO
-            return_dict (`bool`): option for returning tuple rather than KarrasVeOutput class
+            return_dict (`bool`, *optional*, defaults to `True`):
+                Whether or not to return a [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] or `tuple`.
 
         Returns:
             prev_sample (TODO): updated sample in the diffusion chain. derivative (TODO): TODO

src/diffusers/schedulers/scheduling_lms_discrete.py

@@ -29,14 +29,14 @@ from .scheduling_utils import KarrasDiffusionSchedulers, SchedulerMixin
 # Copied from diffusers.schedulers.scheduling_ddpm.DDPMSchedulerOutput with DDPM->LMSDiscrete
 class LMSDiscreteSchedulerOutput(BaseOutput):
     """
-    Output class for the scheduler's step function output.
+    Output class for the scheduler's `step` function output.
 
     Args:
         prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
-            Computed sample (x_{t-1}) of previous timestep. `prev_sample` should be used as next model input in the
+            Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
             denoising loop.
         pred_original_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
-            The predicted denoised sample (x_{0}) based on the model output from the current timestep.
+            The predicted denoised sample `(x_{0})` based on the model output from the current timestep.
             `pred_original_sample` can be used to preview progress or for guidance.
     """
 
@@ -91,39 +91,37 @@ def betas_for_alpha_bar(
 
 class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
     """
-    Linear Multistep Scheduler for discrete beta schedules. Based on the original k-diffusion implementation by
-    Katherine Crowson:
-    https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L181
+    A linear multistep scheduler for discrete beta schedules.
 
-    [`~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`.
-    [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and
-    [`~SchedulerMixin.from_pretrained`] functions.
+    This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
+    methods the library implements for all schedulers such as loading and saving.
 
     Args:
-        num_train_timesteps (`int`): number of diffusion steps used to train the model.
-        beta_start (`float`): the starting `beta` value of inference.
-        beta_end (`float`): the final `beta` value.
-        beta_schedule (`str`):
-            the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
+        num_train_timesteps (`int`, defaults to 1000):
+            The number of diffusion steps to train the model.
+        beta_start (`float`, defaults to 0.0001):
+            The starting `beta` value of inference.
+        beta_end (`float`, defaults to 0.02):
+            The final `beta` value.
+        beta_schedule (`str`, defaults to `"linear"`):
+            The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
             `linear` or `scaled_linear`.
-        trained_betas (`np.ndarray`, optional):
-            option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
+        trained_betas (`np.ndarray`, *optional*):
+            Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`.
         use_karras_sigmas (`bool`, *optional*, defaults to `False`):
-            This parameter controls whether to use Karras sigmas (Karras et al. (2022) scheme) for step sizes in the
-            noise schedule during the sampling process. If True, the sigmas will be determined according to a sequence
-            of noise levels {σi} as defined in Equation (5) of the paper https://arxiv.org/pdf/2206.00364.pdf.
-        prediction_type (`str`, default `epsilon`, optional):
-            prediction type of the scheduler function, one of `epsilon` (predicting the noise of the diffusion
-            process), `sample` (directly predicting the noisy sample`) or `v_prediction` (see section 2.4
-            https://imagen.research.google/video/paper.pdf)
-        timestep_spacing (`str`, default `"linspace"`):
-            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_offset (`int`, default `0`):
-            an offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False`, to make the last step use step 0 for the previous alpha product, as done in
-            stable diffusion.
+            Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. If `True`,
+            the sigmas are determined according to a sequence of noise levels {σi}.
+        prediction_type (`str`, defaults to `epsilon`, *optional*):
+            Prediction type of the scheduler function; can be `epsilon` (predicts the noise of the diffusion process),
+            `sample` (directly predicts the noisy sample`) or `v_prediction` (see section 2.4 of [Imagen
+            Video](https://imagen.research.google/video/paper.pdf) paper).
+        timestep_spacing (`str`, defaults to `"linspace"`):
+            The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
+            Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
+        steps_offset (`int`, defaults to 0):
+            An offset added to the inference steps. You can use a combination of `offset=1` and
+            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
+            Diffusion.
     """
 
     _compatibles = [e.name for e in KarrasDiffusionSchedulers]
@@ -183,14 +181,18 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         self, sample: torch.FloatTensor, timestep: Union[float, torch.FloatTensor]
     ) -> torch.FloatTensor:
         """
-        Scales the denoising model input by `(sigma**2 + 1) ** 0.5` to match the K-LMS algorithm.
+        Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
+        current timestep.
 
         Args:
-            sample (`torch.FloatTensor`): input sample
-            timestep (`float` or `torch.FloatTensor`): the current timestep in the diffusion chain
+            sample (`torch.FloatTensor`):
+                The input sample.
+            timestep (`float` or `torch.FloatTensor`):
+                The current timestep in the diffusion chain.
 
         Returns:
-            `torch.FloatTensor`: scaled input sample
+            `torch.FloatTensor`:
+                A scaled input sample.
         """
         if isinstance(timestep, torch.Tensor):
             timestep = timestep.to(self.timesteps.device)
@@ -202,12 +204,12 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
 
     def get_lms_coefficient(self, order, t, current_order):
         """
-        Compute a linear multistep coefficient.
+        Compute the linear multistep coefficient.
 
         Args:
-            order (TODO):
-            t (TODO):
-            current_order (TODO):
+            order ():
+            t ():
+            current_order ():
         """
 
         def lms_derivative(tau):
@@ -224,13 +226,13 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
 
     def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None):
         """
-        Sets the timesteps used for the diffusion chain. Supporting function to be run before inference.
+        Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
         Args:
             num_inference_steps (`int`):
-                the number of diffusion steps used when generating samples with a pre-trained model.
-            device (`str` or `torch.device`, optional):
-                the device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
+                The number of diffusion steps used when generating samples with a pre-trained model.
+            device (`str` or `torch.device`, *optional*):
+                The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
         """
         self.num_inference_steps = num_inference_steps
 
@@ -322,21 +324,25 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[LMSDiscreteSchedulerOutput, Tuple]:
         """
-        Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
         process from the learned model outputs (most often the predicted noise).
 
         Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
-            timestep (`float`): current timestep in the diffusion chain.
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
+            timestep (`float` or `torch.FloatTensor`):
+                The current discrete timestep in the diffusion chain.
             sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-            order: coefficient for multi-step inference.
-            return_dict (`bool`): option for returning tuple rather than LMSDiscreteSchedulerOutput class
+                A current instance of a sample created by the diffusion process.
+            order (`int`, defaults to 4):
+                The order of the linear multistep method.
+            return_dict (`bool`, *optional*, defaults to `True`):
+                Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or tuple.
 
         Returns:
-            [`~schedulers.scheduling_utils.LMSDiscreteSchedulerOutput`] or `tuple`:
-            [`~schedulers.scheduling_utils.LMSDiscreteSchedulerOutput`] if `return_dict` is True, otherwise a `tuple`.
-            When returning a tuple, the first element is the sample tensor.
+            [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`:
+                If return_dict is `True`, [`~schedulers.scheduling_utils.SchedulerOutput`] is returned, otherwise a
+                tuple is returned where the first element is the sample tensor.
 
         """
         if not self.is_scale_input_called:

src/diffusers/schedulers/scheduling_pndm.py

@@ -71,42 +71,42 @@ def betas_for_alpha_bar(
 
 class PNDMScheduler(SchedulerMixin, ConfigMixin):
     """
-    Pseudo numerical methods for diffusion models (PNDM) proposes using more advanced ODE integration techniques,
-    namely Runge-Kutta method and a linear multi-step method.
+    `PNDMScheduler` uses pseudo numerical methods for diffusion models such as the Runge-Kutta and linear multi-step
+    method.
 
-    [`~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`.
-    [`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
+    This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
+    methods the library implements for all schedulers such as loading and saving.
 
     Args:
-        num_train_timesteps (`int`): number of diffusion steps used to train the model.
-        beta_start (`float`): the starting `beta` value of inference.
-        beta_end (`float`): the final `beta` value.
-        beta_schedule (`str`):
-            the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
+        num_train_timesteps (`int`, defaults to 1000):
+            The number of diffusion steps to train the model.
+        beta_start (`float`, defaults to 0.0001):
+            The starting `beta` value of inference.
+        beta_end (`float`, defaults to 0.02):
+            The final `beta` value.
+        beta_schedule (`str`, defaults to `"linear"`):
+            The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
             `linear`, `scaled_linear`, or `squaredcos_cap_v2`.
-        trained_betas (`np.ndarray`, optional):
-            option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
-        skip_prk_steps (`bool`):
-            allows the scheduler to skip the Runge-Kutta steps that are defined in the original paper as being required
-            before plms steps; defaults to `False`.
-        set_alpha_to_one (`bool`, default `False`):
-            each diffusion step uses the value of alphas product at that step and at the previous one. For the final
-            step there is no previous alpha. When this option is `True` the previous alpha product is fixed to `1`,
-            otherwise it uses the value of alpha at step 0.
-        prediction_type (`str`, default `epsilon`, optional):
-            prediction type of the scheduler function, one of `epsilon` (predicting the noise of the diffusion process)
-            or `v_prediction` (see section 2.4 https://imagen.research.google/video/paper.pdf)
-        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_offset (`int`, default `0`):
-            an offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False`, to make the last step use step 0 for the previous alpha product, as done in
-            stable diffusion.
+        trained_betas (`np.ndarray`, *optional*):
+            Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`.
+        skip_prk_steps (`bool`, defaults to `False`):
+            Allows the scheduler to skip the Runge-Kutta steps defined in the original paper as being required before
+            PLMS steps.
+        set_alpha_to_one (`bool`, defaults to `False`):
+            Each diffusion step uses the alphas product value at that step and at the previous one. For the final step
+            there is no previous alpha. When this option is `True` the previous alpha product is fixed to `1`,
+            otherwise it uses the alpha value at step 0.
+        prediction_type (`str`, defaults to `epsilon`, *optional*):
+            Prediction type of the scheduler function; can be `epsilon` (predicts the noise of the diffusion process)
+            or `v_prediction` (see section 2.4 of [Imagen Video](https://imagen.research.google/video/paper.pdf)
+            paper).
+        timestep_spacing (`str`, defaults to `"leading"`):
+            The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
+            Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
+        steps_offset (`int`, defaults to 0):
+            An offset added to the inference steps. You can use a combination of `offset=1` and
+            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
+            Diffusion.
     """
 
     _compatibles = [e.name for e in KarrasDiffusionSchedulers]
@@ -169,11 +169,13 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
 
     def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None):
         """
-        Sets the discrete timesteps used for the diffusion chain. Supporting function to be run before inference.
+        Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
         Args:
             num_inference_steps (`int`):
-                the number of diffusion steps used when generating samples with a pre-trained model.
+                The number of diffusion steps used when generating samples with a pre-trained model.
+            device (`str` or `torch.device`, *optional*):
+                The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
         """
 
         self.num_inference_steps = num_inference_steps
@@ -233,22 +235,24 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
-        Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion
-        process from the learned model outputs (most often the predicted noise).
-
-        This function calls `step_prk()` or `step_plms()` depending on the internal variable `counter`.
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
+        process from the learned model outputs (most often the predicted noise), and calls [`~PNDMScheduler.step_prk`]
+        or [`~PNDMScheduler.step_plms`] depending on the internal variable `counter`.
 
         Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
-            timestep (`int`): current discrete timestep in the diffusion chain.
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
+            timestep (`int`):
+                The current discrete timestep in the diffusion chain.
             sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-            return_dict (`bool`): option for returning tuple rather than SchedulerOutput class
+                A current instance of a sample created by the diffusion process.
+            return_dict (`bool`):
+                Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`.
 
         Returns:
             [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`:
-            [`~schedulers.scheduling_utils.SchedulerOutput`] if `return_dict` is True, otherwise a `tuple`. When
-            returning a tuple, the first element is the sample tensor.
+                If return_dict is `True`, [`~schedulers.scheduling_utils.SchedulerOutput`] is returned, otherwise a
+                tuple is returned where the first element is the sample tensor.
 
         """
         if self.counter < len(self.prk_timesteps) and not self.config.skip_prk_steps:
@@ -264,19 +268,24 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
-        Step function propagating the sample with the Runge-Kutta method. RK takes 4 forward passes to approximate the
-        solution to the differential equation.
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with
+        the Runge-Kutta method. It performs four forward passes to approximate the solution to the differential
+        equation.
 
         Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
-            timestep (`int`): current discrete timestep in the diffusion chain.
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
+            timestep (`int`):
+                The current discrete timestep in the diffusion chain.
             sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-            return_dict (`bool`): option for returning tuple rather than SchedulerOutput class
+                A current instance of a sample created by the diffusion process.
+            return_dict (`bool`):
+                Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or tuple.
 
         Returns:
-            [`~scheduling_utils.SchedulerOutput`] or `tuple`: [`~scheduling_utils.SchedulerOutput`] if `return_dict` is
-            True, otherwise a `tuple`. When returning a tuple, the first element is the sample tensor.
+            [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`:
+                If return_dict is `True`, [`~schedulers.scheduling_utils.SchedulerOutput`] is returned, otherwise a
+                tuple is returned where the first element is the sample tensor.
 
         """
         if self.num_inference_steps is None:
@@ -319,19 +328,23 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
-        Step function propagating the sample with the linear multi-step method. This has one forward pass with multiple
-        times to approximate the solution.
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with
+        the linear multistep method. It performs one forward pass multiple times to approximate the solution.
 
         Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
-            timestep (`int`): current discrete timestep in the diffusion chain.
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
+            timestep (`int`):
+                The current discrete timestep in the diffusion chain.
             sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-            return_dict (`bool`): option for returning tuple rather than SchedulerOutput class
+                A current instance of a sample created by the diffusion process.
+            return_dict (`bool`):
+                Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or tuple.
 
         Returns:
-            [`~scheduling_utils.SchedulerOutput`] or `tuple`: [`~scheduling_utils.SchedulerOutput`] if `return_dict` is
-            True, otherwise a `tuple`. When returning a tuple, the first element is the sample tensor.
+            [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`:
+                If return_dict is `True`, [`~schedulers.scheduling_utils.SchedulerOutput`] is returned, otherwise a
+                tuple is returned where the first element is the sample tensor.
 
         """
         if self.num_inference_steps is None:
@@ -384,10 +397,12 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
         current timestep.
 
         Args:
-            sample (`torch.FloatTensor`): input sample
+            sample (`torch.FloatTensor`):
+                The input sample.
 
         Returns:
-            `torch.FloatTensor`: scaled input sample
+            `torch.FloatTensor`:
+                A scaled input sample.
         """
         return sample
 

src/diffusers/schedulers/scheduling_repaint.py

@@ -89,32 +89,28 @@ def betas_for_alpha_bar(
 
 class RePaintScheduler(SchedulerMixin, ConfigMixin):
     """
-    RePaint is a schedule for DDPM inpainting inside a given mask.
+    `RePaintScheduler` is a scheduler for DDPM inpainting inside a given mask.
 
-    [`~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`.
-    [`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/pdf/2201.09865.pdf
+    This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
+    methods the library implements for all schedulers such as loading and saving.
 
     Args:
-        num_train_timesteps (`int`): number of diffusion steps used to train the model.
-        beta_start (`float`): the starting `beta` value of inference.
-        beta_end (`float`): the final `beta` value.
-        beta_schedule (`str`):
-            the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
-            `linear`, `scaled_linear`, `squaredcos_cap_v2` or `sigmoid`.
+        num_train_timesteps (`int`, defaults to 1000):
+            The number of diffusion steps to train the model.
+        beta_start (`float`, defaults to 0.0001):
+            The starting `beta` value of inference.
+        beta_end (`float`, defaults to 0.02):
+            The final `beta` value.
+        beta_schedule (`str`, defaults to `"linear"`):
+            The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
+            `linear`, `scaled_linear`, `squaredcos_cap_v2`, or `sigmoid`.
         eta (`float`):
-            The weight of noise for added noise in a diffusion step. Its value is between 0.0 and 1.0 -0.0 is DDIM and
-            1.0 is DDPM scheduler respectively.
-        trained_betas (`np.ndarray`, optional):
-            option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
-        variance_type (`str`):
-            options to clip the variance used when adding noise to the denoised sample. Choose from `fixed_small`,
-            `fixed_small_log`, `fixed_large`, `fixed_large_log`, `learned` or `learned_range`.
-        clip_sample (`bool`, default `True`):
-            option to clip predicted sample between -1 and 1 for numerical stability.
+            The weight of noise for added noise in diffusion step. If its value is between 0.0 and 1.0 it corresponds
+            to the DDIM scheduler, and if its value is between -0.0 and 1.0 it corresponds to the DDPM scheduler.
+        trained_betas (`np.ndarray`, *optional*):
+            Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`.
+        clip_sample (`bool`, defaults to `True`):
+            Clip the predicted sample between -1 and 1 for numerical stability.
 
     """
 
@@ -171,11 +167,14 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
         current timestep.
 
         Args:
-            sample (`torch.FloatTensor`): input sample
-            timestep (`int`, optional): current timestep
+            sample (`torch.FloatTensor`):
+                The input sample.
+            timestep (`int`, *optional*):
+                The current timestep in the diffusion chain.
 
         Returns:
-            `torch.FloatTensor`: scaled input sample
+            `torch.FloatTensor`:
+                A scaled input sample.
         """
         return sample
 
@@ -186,6 +185,23 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
         jump_n_sample: int = 10,
         device: Union[str, torch.device] = None,
     ):
+        """
+        Sets the discrete timesteps used for the diffusion chain (to be run before inference).
+
+        Args:
+            num_inference_steps (`int`):
+                The number of diffusion steps used when generating samples with a pre-trained model. If used,
+                `timesteps` must be `None`.
+            jump_length (`int`, defaults to 10):
+                The number of steps taken forward in time before going backward in time for a single jump (“j” in
+                RePaint paper). Take a look at Figure 9 and 10 in the paper.
+            jump_n_sample (`int`, defaults to 10):
+                The number of times to make a forward time jump for a given chosen time sample. Take a look at Figure 9
+                and 10 in the paper.
+            device (`str` or `torch.device`, *optional*):
+                The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
+
+        """
         num_inference_steps = min(self.config.num_train_timesteps, num_inference_steps)
         self.num_inference_steps = num_inference_steps
 
@@ -239,27 +255,29 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[RePaintSchedulerOutput, Tuple]:
         """
-        Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
         process from the learned model outputs (most often the predicted noise).
 
         Args:
-            model_output (`torch.FloatTensor`): direct output from learned
-                diffusion model.
-            timestep (`int`): current discrete timestep in the diffusion chain.
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
+            timestep (`int`):
+                The current discrete timestep in the diffusion chain.
             sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
+                A current instance of a sample created by the diffusion process.
             original_image (`torch.FloatTensor`):
-                the original image to inpaint on.
+                The original image to inpaint on.
             mask (`torch.FloatTensor`):
-                the mask where 0.0 values define which part of the original image to inpaint (change).
-            generator (`torch.Generator`, *optional*): random number generator.
-            return_dict (`bool`): option for returning tuple rather than
-                DDPMSchedulerOutput class
+                The mask where a value of 0.0 indicates which part of the original image to inpaint.
+            generator (`torch.Generator`, *optional*):
+                A random number generator.
+            return_dict (`bool`, *optional*, defaults to `True`):
+                Whether or not to return a [`~schedulers.scheduling_repaint.RePaintSchedulerOutput`] or `tuple`.
 
         Returns:
-            [`~schedulers.scheduling_utils.RePaintSchedulerOutput`] or `tuple`:
-            [`~schedulers.scheduling_utils.RePaintSchedulerOutput`] if `return_dict` is True, otherwise a `tuple`. When
-            returning a tuple, the first element is the sample tensor.
+            [`~schedulers.scheduling_repaint.RePaintSchedulerOutput`] or `tuple`:
+                If return_dict is `True`, [`~schedulers.scheduling_repaint.RePaintSchedulerOutput`] is returned,
+                otherwise a tuple is returned where the first element is the sample tensor.
 
         """
         t = timestep

src/diffusers/schedulers/scheduling_sde_ve.py

@@ -28,14 +28,14 @@ from .scheduling_utils import SchedulerMixin, SchedulerOutput
 @dataclass
 class SdeVeOutput(BaseOutput):
     """
-    Output class for the ScoreSdeVeScheduler's step function output.
+    Output class for the scheduler's `step` function output.
 
     Args:
         prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
-            Computed sample (x_{t-1}) of previous timestep. `prev_sample` should be used as next model input in the
+            Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
             denoising loop.
         prev_sample_mean (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
-            Mean averaged `prev_sample`. Same as `prev_sample`, only mean-averaged over previous timesteps.
+            Mean averaged `prev_sample` over previous timesteps.
     """
 
     prev_sample: torch.FloatTensor
@@ -44,26 +44,25 @@ class SdeVeOutput(BaseOutput):
 
 class ScoreSdeVeScheduler(SchedulerMixin, ConfigMixin):
     """
-    The variance exploding stochastic differential equation (SDE) scheduler.
+    `ScoreSdeVeScheduler` is a variance exploding stochastic differential equation (SDE) scheduler.
 
-    For more information, see the original paper: https://arxiv.org/abs/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`.
-    [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and
-    [`~SchedulerMixin.from_pretrained`] functions.
+    This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
+    methods the library implements for all schedulers such as loading and saving.
 
     Args:
-        num_train_timesteps (`int`): number of diffusion steps used to train the model.
-        snr (`float`):
-            coefficient weighting the step from the model_output sample (from the network) to the random noise.
-        sigma_min (`float`):
-                initial noise scale for sigma sequence in sampling procedure. The minimum sigma should mirror the
-                distribution of the data.
-        sigma_max (`float`): maximum value used for the range of continuous timesteps passed into the model.
-        sampling_eps (`float`): the end value of sampling, where timesteps decrease progressively from 1 to
-        epsilon.
-        correct_steps (`int`): number of correction steps performed on a produced sample.
+        num_train_timesteps (`int`, defaults to 1000):
+            The number of diffusion steps to train the model.
+        snr (`float`, defaults to 0.15):
+            A coefficient weighting the step from the `model_output` sample (from the network) to the random noise.
+        sigma_min (`float`, defaults to 0.01):
+            The initial noise scale for the sigma sequence in the sampling procedure. The minimum sigma should mirror
+            the distribution of the data.
+        sigma_max (`float`, defaults to 1348.0):
+            The maximum value used for the range of continuous timesteps passed into the model.
+        sampling_eps (`float`, defaults to 1e-5):
+            The end value of sampling where timesteps decrease progressively from 1 to epsilon.
+        correct_steps (`int`, defaults to 1):
+            The number of correction steps performed on a produced sample.
     """
 
     order = 1
@@ -92,11 +91,14 @@ class ScoreSdeVeScheduler(SchedulerMixin, ConfigMixin):
         current timestep.
 
         Args:
-            sample (`torch.FloatTensor`): input sample
-            timestep (`int`, optional): current timestep
+            sample (`torch.FloatTensor`):
+                The input sample.
+            timestep (`int`, *optional*):
+                The current timestep in the diffusion chain.
 
         Returns:
-            `torch.FloatTensor`: scaled input sample
+            `torch.FloatTensor`:
+                A scaled input sample.
         """
         return sample
 
@@ -104,13 +106,15 @@ class ScoreSdeVeScheduler(SchedulerMixin, ConfigMixin):
         self, num_inference_steps: int, sampling_eps: float = None, device: Union[str, torch.device] = None
     ):
         """
-        Sets the continuous timesteps used for the diffusion chain. Supporting function to be run before inference.
+        Sets the continuous timesteps used for the diffusion chain (to be run before inference).
 
         Args:
             num_inference_steps (`int`):
-                the number of diffusion steps used when generating samples with a pre-trained model.
-            sampling_eps (`float`, optional):
-                final timestep value (overrides value given at Scheduler instantiation).
+                The number of diffusion steps used when generating samples with a pre-trained model.
+            sampling_eps (`float`, *optional*):
+                The final timestep value (overrides value given during scheduler instantiation).
+            device (`str` or `torch.device`, *optional*):
+                The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
 
         """
         sampling_eps = sampling_eps if sampling_eps is not None else self.config.sampling_eps
@@ -121,19 +125,18 @@ class ScoreSdeVeScheduler(SchedulerMixin, ConfigMixin):
         self, num_inference_steps: int, sigma_min: float = None, sigma_max: float = None, sampling_eps: float = None
     ):
         """
-        Sets the noise scales used for the diffusion chain. Supporting function to be run before inference.
-
-        The sigmas control the weight of the `drift` and `diffusion` components of sample update.
+        Sets the noise scales used for the diffusion chain (to be run before inference). The sigmas control the weight
+        of the `drift` and `diffusion` components of the sample update.
 
         Args:
             num_inference_steps (`int`):
-                the number of diffusion steps used when generating samples with a pre-trained model.
+                The number of diffusion steps used when generating samples with a pre-trained model.
             sigma_min (`float`, optional):
-                initial noise scale value (overrides value given at Scheduler instantiation).
+                The initial noise scale value (overrides value given during scheduler instantiation).
             sigma_max (`float`, optional):
-                final noise scale value (overrides value given at Scheduler instantiation).
+                The final noise scale value (overrides value given during scheduler instantiation).
             sampling_eps (`float`, optional):
-                final timestep value (overrides value given at Scheduler instantiation).
+                The final timestep value (overrides value given during scheduler instantiation).
 
         """
         sigma_min = sigma_min if sigma_min is not None else self.config.sigma_min
@@ -162,20 +165,25 @@ class ScoreSdeVeScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[SdeVeOutput, Tuple]:
         """
-        Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
         process from the learned model outputs (most often the predicted noise).
 
         Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
-            timestep (`int`): current discrete timestep in the diffusion chain.
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
+            timestep (`int`):
+                The current discrete timestep in the diffusion chain.
             sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-            generator: random number generator.
-            return_dict (`bool`): option for returning tuple rather than SchedulerOutput class
+                A current instance of a sample created by the diffusion process.
+            generator (`torch.Generator`, *optional*):
+                A random number generator.
+            return_dict (`bool`, *optional*, defaults to `True`):
+                Whether or not to return a [`~schedulers.scheduling_sde_ve.SdeVeOutput`] or `tuple`.
 
         Returns:
-            [`~schedulers.scheduling_sde_ve.SdeVeOutput`] or `tuple`: [`~schedulers.scheduling_sde_ve.SdeVeOutput`] if
-            `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is the sample tensor.
+            [`~schedulers.scheduling_sde_ve.SdeVeOutput`] or `tuple`:
+                If return_dict is `True`, [`~schedulers.scheduling_sde_ve.SdeVeOutput`] is returned, otherwise a tuple
+                is returned where the first element is the sample tensor.
 
         """
         if self.timesteps is None:
@@ -224,19 +232,23 @@ class ScoreSdeVeScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
-        Correct the predicted sample based on the output model_output of the network. This is often run repeatedly
-        after making the prediction for the previous timestep.
+        Correct the predicted sample based on the `model_output` of the network. This is often run repeatedly after
+        making the prediction for the previous timestep.
 
         Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
             sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-            generator: random number generator.
-            return_dict (`bool`): option for returning tuple rather than SchedulerOutput class
+                A current instance of a sample created by the diffusion process.
+            generator (`torch.Generator`, *optional*):
+                A random number generator.
+            return_dict (`bool`, *optional*, defaults to `True`):
+                Whether or not to return a [`~schedulers.scheduling_sde_ve.SdeVeOutput`] or `tuple`.
 
         Returns:
-            [`~schedulers.scheduling_sde_ve.SdeVeOutput`] or `tuple`: [`~schedulers.scheduling_sde_ve.SdeVeOutput`] if
-            `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is the sample tensor.
+            [`~schedulers.scheduling_sde_ve.SdeVeOutput`] or `tuple`:
+                If return_dict is `True`, [`~schedulers.scheduling_sde_ve.SdeVeOutput`] is returned, otherwise a tuple
+                is returned where the first element is the sample tensor.
 
         """
         if self.timesteps is None:

src/diffusers/schedulers/scheduling_sde_vp.py

@@ -26,17 +26,18 @@ from .scheduling_utils import SchedulerMixin
 
 class ScoreSdeVpScheduler(SchedulerMixin, ConfigMixin):
     """
-    The variance preserving stochastic differential equation (SDE) scheduler.
-
-    [`~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`.
-    [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and
-    [`~SchedulerMixin.from_pretrained`] functions.
-
-    For more information, see the original paper: https://arxiv.org/abs/2011.13456
-
-    UNDER CONSTRUCTION
-
+    `ScoreSdeVpScheduler` is a variance preserving stochastic differential equation (SDE) scheduler.
+
+    This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
+    methods the library implements for all schedulers such as loading and saving.
+
+    Args:
+        num_train_timesteps (`int`, defaults to 2000):
+            The number of diffusion steps to train the model.
+        beta_min (`int`, defaults to 0.1):
+        beta_max (`int`, defaults to 20):
+        sampling_eps (`int`, defaults to 1e-3):
+            The end value of sampling where timesteps decrease progressively from 1 to epsilon.
     """
 
     order = 1
@@ -48,9 +49,29 @@ class ScoreSdeVpScheduler(SchedulerMixin, ConfigMixin):
         self.timesteps = None
 
     def set_timesteps(self, num_inference_steps, device: Union[str, torch.device] = None):
+        """
+        Sets the continuous timesteps used for the diffusion chain (to be run before inference).
+
+        Args:
+            num_inference_steps (`int`):
+                The number of diffusion steps used when generating samples with a pre-trained model.
+            device (`str` or `torch.device`, *optional*):
+                The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
+        """
         self.timesteps = torch.linspace(1, self.config.sampling_eps, num_inference_steps, device=device)
 
     def step_pred(self, score, x, t, generator=None):
+        """
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
+        process from the learned model outputs (most often the predicted noise).
+
+        Args:
+            score ():
+            x ():
+            t ():
+            generator (`torch.Generator`, *optional*):
+                A random number generator.
+        """
         if self.timesteps is None:
             raise ValueError(
                 "`self.timesteps` is not set, you need to run 'set_timesteps' after creating the scheduler"

src/diffusers/schedulers/scheduling_unclip.py

@@ -28,14 +28,14 @@ from .scheduling_utils import SchedulerMixin
 # Copied from diffusers.schedulers.scheduling_ddpm.DDPMSchedulerOutput with DDPM->UnCLIP
 class UnCLIPSchedulerOutput(BaseOutput):
     """
-    Output class for the scheduler's step function output.
+    Output class for the scheduler's `step` function output.
 
     Args:
         prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
-            Computed sample (x_{t-1}) of previous timestep. `prev_sample` should be used as next model input in the
+            Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
             denoising loop.
         pred_original_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
-            The predicted denoised sample (x_{0}) based on the model output from the current timestep.
+            The predicted denoised sample `(x_{0})` based on the model output from the current timestep.
             `pred_original_sample` can be used to preview progress or for guidance.
     """
 

src/diffusers/schedulers/scheduling_utils.py

@@ -49,11 +49,11 @@ class KarrasDiffusionSchedulers(Enum):
 @dataclass
 class SchedulerOutput(BaseOutput):
     """
-    Base class for the scheduler's step function output.
+    Base class for the output of a scheduler's `step` function.
 
     Args:
         prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
-            Computed sample (x_{t-1}) of previous timestep. `prev_sample` should be used as next model input in the
+            Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
             denoising loop.
     """
 
@@ -62,11 +62,17 @@ class SchedulerOutput(BaseOutput):
 
 class SchedulerMixin:
     """
-    Mixin containing common functions for the schedulers.
+    Base class for all schedulers.
+
+    [`SchedulerMixin`] contains common functions shared by all schedulers such as general loading and saving
+    functionalities.
+
+    [`ConfigMixin`] takes care of storing the configuration attributes (like `num_train_timesteps`) that are passed to
+    the scheduler's `__init__` function, and the attributes can be accessed by `scheduler.config.num_train_timesteps`.
 
     Class attributes:
-        - **_compatibles** (`List[str]`) -- A list of classes that are compatible with the parent class, so that
-          `from_config` can be used from a class different than the one used to save the config (should be overridden
+        - **_compatibles** (`List[str]`) -- A list of scheduler classes that are compatible with the parent scheduler
+          class. Use [`~ConfigMixin.from_config`] to load a different compatible scheduler class (should be overridden
           by parent class).
     """
 
@@ -83,56 +89,50 @@ class SchedulerMixin:
         **kwargs,
     ):
         r"""
-        Instantiate a Scheduler class from a pre-defined JSON configuration file inside a directory or Hub repo.
+        Instantiate a scheduler from a pre-defined JSON configuration file in a local directory or Hub repository.
 
         Parameters:
             pretrained_model_name_or_path (`str` or `os.PathLike`, *optional*):
                 Can be either:
 
-                    - A string, the *model id* of a model repo on huggingface.co. Valid model ids should have an
-                      organization name, like `google/ddpm-celebahq-256`.
-                    - A path to a *directory* containing the schedluer configurations saved using
-                      [`~SchedulerMixin.save_pretrained`], e.g., `./my_model_directory/`.
+                    - A string, the *model id* (for example `google/ddpm-celebahq-256`) of a pretrained model hosted on
+                      the Hub.
+                    - A path to a *directory* (for example `./my_model_directory`) containing the scheduler
+                      configuration saved with [`~SchedulerMixin.save_pretrained`].
             subfolder (`str`, *optional*):
-                In case the relevant files are located inside a subfolder of the model repo (either remote in
-                huggingface.co or downloaded locally), you can specify the folder name here.
+                The subfolder location of a model file within a larger model repository on the Hub or locally.
             return_unused_kwargs (`bool`, *optional*, defaults to `False`):
                 Whether kwargs that are not consumed by the Python class should be returned or not.
             cache_dir (`Union[str, os.PathLike]`, *optional*):
-                Path to a directory in which a downloaded pretrained model configuration should be cached if the
-                standard cache should not be used.
+                Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
+                is not used.
             force_download (`bool`, *optional*, defaults to `False`):
                 Whether or not to force the (re-)download of the model weights and configuration files, overriding the
                 cached versions if they exist.
             resume_download (`bool`, *optional*, defaults to `False`):
-                Whether or not to delete incompletely received files. Will attempt to resume the download if such a
-                file exists.
+                Whether or not to resume downloading the model weights and configuration files. If set to `False`, any
+                incompletely downloaded files are deleted.
             proxies (`Dict[str, str]`, *optional*):
-                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
+                A dictionary of proxy servers to use by protocol or endpoint, for example, `{'http': 'foo.bar:3128',
                 'http://hostname': 'foo.bar:4012'}`. The proxies are used on each request.
             output_loading_info(`bool`, *optional*, defaults to `False`):
                 Whether or not to also return a dictionary containing missing keys, unexpected keys and error messages.
             local_files_only(`bool`, *optional*, defaults to `False`):
-                Whether or not to only look at local files (i.e., do not try to download the model).
+                Whether to only load local model weights and configuration files or not. If set to `True`, the model
+                won't be downloaded from the Hub.
             use_auth_token (`str` or *bool*, *optional*):
-                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
-                when running `transformers-cli login` (stored in `~/.huggingface`).
+                The token to use as HTTP bearer authorization for remote files. If `True`, the token generated from
+                `diffusers-cli login` (stored in `~/.huggingface`) is used.
             revision (`str`, *optional*, defaults to `"main"`):
-                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
-                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
-                identifier allowed by git.
-
-        <Tip>
-
-         It is required to be logged in (`huggingface-cli login`) when you want to use private or [gated
-         models](https://huggingface.co/docs/hub/models-gated#gated-models).
-
-        </Tip>
+                The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
+                allowed by Git.
 
         <Tip>
 
-        Activate the special ["offline-mode"](https://huggingface.co/transformers/installation.html#offline-mode) to
-        use this method in a firewalled environment.
+        To use private or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models), log-in with
+        `huggingface-cli login`. You can also activate the special
+        ["offline-mode"](https://huggingface.co/diffusers/installation.html#offline-mode) to use this method in a
+        firewalled environment.
 
         </Tip>
 
@@ -148,12 +148,12 @@ class SchedulerMixin:
 
     def save_pretrained(self, save_directory: Union[str, os.PathLike], push_to_hub: bool = False, **kwargs):
         """
-        Save a scheduler configuration object to the directory `save_directory`, so that it can be re-loaded using the
+        Save a scheduler configuration object to a directory so that it can be reloaded using the
         [`~SchedulerMixin.from_pretrained`] class method.
 
         Args:
             save_directory (`str` or `os.PathLike`):
-                Directory where the configuration JSON file will be saved (will be created if it does not exist).
+                Directory to save a configuration JSON file to. Will be created if it doesn't exist.
         """
         self.save_config(save_directory=save_directory, push_to_hub=push_to_hub, **kwargs)
 

tests/others/test_check_copies.py

@@ -31,14 +31,14 @@ import check_copies  # noqa: E402
 # This is the reference code that will be used in the tests.
 # If DDPMSchedulerOutput is changed in scheduling_ddpm.py, this code needs to be manually updated.
 REFERENCE_CODE = """    \"""
-    Output class for the scheduler's step function output.
+    Output class for the scheduler's `step` function output.
 
     Args:
         prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
-            Computed sample (x_{t-1}) of previous timestep. `prev_sample` should be used as next model input in the
+            Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
             denoising loop.
         pred_original_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
-            The predicted denoised sample (x_{0}) based on the model output from the current timestep.
+            The predicted denoised sample `(x_{0})` based on the model output from the current timestep.
             `pred_original_sample` can be used to preview progress or for guidance.
     \"""