diffusers 0.19.3__py3-none-any.whl → 0.20.1__py3-none-any.whl

diffusers/schedulers/scheduling_euler_discrete.py

@@ -31,14 +31,14 @@ logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 # Copied from diffusers.schedulers.scheduling_ddpm.DDPMSchedulerOutput with DDPM->EulerDiscrete
 class EulerDiscreteSchedulerOutput(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.
     """
 
@@ -93,42 +93,40 @@ def betas_for_alpha_bar(
 
 class EulerDiscreteScheduler(SchedulerMixin, ConfigMixin):
     """
-    Euler scheduler (Algorithm 2) from Karras et al. (2022) https://arxiv.org/abs/2206.00364. . Based on the original
-    k-diffusion implementation by Katherine Crowson:
-    https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L51
+    Euler 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.
+    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.
-        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)
-        interpolation_type (`str`, default `"linear"`, optional):
-            interpolation type to compute intermediate sigmas for the scheduler denoising steps. Should be one of
-            [`"linear"`, `"log_linear"`].
+        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).
+        interpolation_type(`str`, defaults to `"linear"`, *optional*):
+            The interpolation type to compute intermediate sigmas for the scheduler denoising steps. Should be on of
+            `"linear"` or `"log_linear"`.
         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.
-        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}.
+        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]
@@ -189,14 +187,18 @@ class EulerDiscreteScheduler(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 Euler algorithm.
+        Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
+        current timestep. Scales the denoising model input by `(sigma**2 + 1) ** 0.5` to match the Euler algorithm.
 
         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 (`int`, *optional*):
+                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)
@@ -210,13 +212,13 @@ class EulerDiscreteScheduler(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
 
@@ -317,26 +319,31 @@ class EulerDiscreteScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[EulerDiscreteSchedulerOutput, 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`):
+                The current discrete timestep in the diffusion chain.
             sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-            s_churn (`float`)
-            s_tmin  (`float`)
-            s_tmax  (`float`)
-            s_noise (`float`)
-            generator (`torch.Generator`, optional): Random number generator.
-            return_dict (`bool`): option for returning tuple rather than EulerDiscreteSchedulerOutput class
+                A current instance of a sample created by the diffusion process.
+            s_churn (`float`):
+            s_tmin  (`float`):
+            s_tmax  (`float`):
+            s_noise (`float`, defaults to 1.0):
+                Scaling factor for noise added to the sample.
+            generator (`torch.Generator`, *optional*):
+                A random number generator.
+            return_dict (`bool`):
+                Whether or not to return a [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] or
+                tuple.
 
         Returns:
-            [`~schedulers.scheduling_utils.EulerDiscreteSchedulerOutput`] or `tuple`:
-            [`~schedulers.scheduling_utils.EulerDiscreteSchedulerOutput`] if `return_dict` is True, otherwise a
-            `tuple`. When returning a tuple, the first element is the sample tensor.
-
+            [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] or `tuple`:
+                If return_dict is `True`, [`~schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput`] is
+                returned, otherwise a tuple is returned where the first element is the sample tensor.
         """
 
         if (

diffusers/schedulers/scheduling_heun_discrete.py

@@ -70,41 +70,41 @@ def betas_for_alpha_bar(
 
 class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
     """
-    Implements Algorithm 2 (Heun steps) from Karras et al. (2022). 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#L90
+    Scheduler with Heun steps 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.
-        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).
-        clip_sample (`bool`, default `True`):
-            option to clip predicted sample for numerical stability.
-        clip_sample_range (`float`, default `1.0`):
-            the maximum magnitude for sample clipping. Valid only when `clip_sample=True`.
+        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).
+        clip_sample (`bool`, defaults to `True`):
+            Clip the predicted sample for numerical stability.
+        clip_sample_range (`float`, defaults to 1.0):
+            The maximum magnitude for sample clipping. Valid only when `clip_sample=True`.
         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.
-        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}.
+        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]
@@ -181,12 +181,18 @@ class HeunDiscreteScheduler(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)
 
@@ -201,13 +207,13 @@ class HeunDiscreteScheduler(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
 
@@ -312,17 +318,23 @@ class HeunDiscreteScheduler(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)
 

diffusers/schedulers/scheduling_ipndm.py

@@ -24,18 +24,16 @@ from .scheduling_utils import SchedulerMixin, SchedulerOutput
 
 class IPNDMScheduler(SchedulerMixin, ConfigMixin):
     """
-    Improved Pseudo numerical methods for diffusion models (iPNDM) ported from @crowsonkb's amazing k-diffusion
-    [library](https://github.com/crowsonkb/v-diffusion-pytorch/blob/987f8985e38208345c1959b0ea767a625831cc9b/diffusion/sampling.py#L296)
+    A fourth-order Improved Pseudo Linear Multistep 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 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.
+        num_train_timesteps (`int`, defaults to 1000):
+            The number of diffusion steps to train the model.
+        trained_betas (`np.ndarray`, *optional*):
+            Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`.
     """
 
     order = 1
@@ -60,11 +58,13 @@ class IPNDMScheduler(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
         steps = torch.linspace(1, 0, num_inference_steps + 1)[:-1]
@@ -90,20 +90,23 @@ class IPNDMScheduler(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:
             raise ValueError(
@@ -138,10 +141,12 @@ class IPNDMScheduler(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
 

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)