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

diffusers/schedulers/scheduling_ddim_parallel.py

@@ -31,14 +31,14 @@ from .scheduling_utils import KarrasDiffusionSchedulers, SchedulerMixin
 # Copied from diffusers.schedulers.scheduling_ddpm.DDPMSchedulerOutput
 class DDIMParallelSchedulerOutput(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.
     """
 
@@ -250,11 +250,14 @@ class DDIMParallelScheduler(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
 
@@ -320,11 +323,11 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
     # Copied from diffusers.schedulers.scheduling_ddim.DDIMScheduler.set_timesteps
     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.
         """
 
         if num_inference_steps > self.config.num_train_timesteps:

diffusers/schedulers/scheduling_ddpm.py

@@ -29,14 +29,14 @@ from .scheduling_utils import KarrasDiffusionSchedulers, SchedulerMixin
 @dataclass
 class DDPMSchedulerOutput(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.
     """
 
@@ -90,52 +90,46 @@ def betas_for_alpha_bar(
 
 class DDPMScheduler(SchedulerMixin, ConfigMixin):
     """
-    Denoising diffusion probabilistic models (DDPMs) explores the connections between denoising score matching and
-    Langevin dynamics sampling.
+    `DDPMScheduler` explores the connections between denoising score matching and Langevin dynamics sampling.
 
-    [`~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/2006.11239
+    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`.
-        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 for numerical stability.
-        clip_sample_range (`float`, default `1.0`):
-            the maximum magnitude for sample clipping. Valid only when `clip_sample=True`.
-        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)
-        thresholding (`bool`, default `False`):
-            whether to use the "dynamic thresholding" method (introduced by Imagen, https://arxiv.org/abs/2205.11487).
-            Note that the thresholding method is unsuitable for latent-space diffusion models (such as
-            stable-diffusion).
-        dynamic_thresholding_ratio (`float`, default `0.995`):
-            the ratio for the dynamic thresholding method. Default is `0.995`, the same as Imagen
-            (https://arxiv.org/abs/2205.11487). Valid only when `thresholding=True`.
-        sample_max_value (`float`, default `1.0`):
-            the threshold value for dynamic thresholding. Valid only when `thresholding=True`.
-        timestep_spacing (`str`, default `"leading"`):
-            The way the timesteps should be scaled. Refer to Table 2. of [Common Diffusion Noise Schedules and Sample
-            Steps are Flawed](https://arxiv.org/abs/2305.08891) for more information.
-        steps_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.
+        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`.
+        variance_type (`str`, defaults to `"fixed_small"`):
+            Clip the variance 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`, 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`.
+        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).
+        thresholding (`bool`, defaults to `False`):
+            Whether to use the "dynamic thresholding" method. This is unsuitable for latent-space diffusion models such
+            as Stable Diffusion.
+        dynamic_thresholding_ratio (`float`, defaults to 0.995):
+            The ratio for the dynamic thresholding method. Valid only when `thresholding=True`.
+        sample_max_value (`float`, defaults to 1.0):
+            The threshold value for dynamic thresholding. Valid only when `thresholding=True`.
+        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]
@@ -198,11 +192,14 @@ class DDPMScheduler(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
 
@@ -213,18 +210,18 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
         timesteps: Optional[List[int]] = 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 (`Optional[int]`):
-                the number of diffusion steps used when generating samples with a pre-trained model. If passed, then
+            num_inference_steps (`int`):
+                The number of diffusion steps used when generating samples with a pre-trained model. If used,
                 `timesteps` must be `None`.
-            device (`str` or `torch.device`, optional):
-                the device to which the timesteps are moved to.
-            custom_timesteps (`List[int]`, optional):
-                custom timesteps used to support arbitrary spacing between timesteps. If `None`, then the default
-                timestep spacing strategy of equal spacing between timesteps is used. If passed, `num_inference_steps`
-                must be `None`.
+            device (`str` or `torch.device`, *optional*):
+                The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
+            timesteps (`List[int]`, *optional*):
+                Custom timesteps used to support arbitrary spacing between timesteps. If `None`, then the default
+                timestep spacing strategy of equal spacing between timesteps is used. If `timesteps` is passed,
+                `num_inference_steps` must be `None`.
 
         """
         if num_inference_steps is not None and timesteps is not None:
@@ -364,21 +361,25 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[DDPMSchedulerOutput, 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 (`float`):
+                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 DDPMSchedulerOutput 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_ddpm.DDPMSchedulerOutput`] or `tuple`.
 
         Returns:
-            [`~schedulers.scheduling_utils.DDPMSchedulerOutput`] or `tuple`:
-            [`~schedulers.scheduling_utils.DDPMSchedulerOutput`] if `return_dict` is True, otherwise a `tuple`. When
-            returning a tuple, the first element is the sample tensor.
+            [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] or `tuple`:
+                If return_dict is `True`, [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] is returned, otherwise a
+                tuple is returned where the first element is the sample tensor.
 
         """
         t = timestep

diffusers/schedulers/scheduling_ddpm_parallel.py

@@ -30,14 +30,14 @@ from .scheduling_utils import KarrasDiffusionSchedulers, SchedulerMixin
 # Copied from diffusers.schedulers.scheduling_ddpm.DDPMSchedulerOutput
 class DDPMParallelSchedulerOutput(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.
     """
 
@@ -203,11 +203,14 @@ class DDPMParallelScheduler(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
 
@@ -219,18 +222,18 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         timesteps: Optional[List[int]] = 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 (`Optional[int]`):
-                the number of diffusion steps used when generating samples with a pre-trained model. If passed, then
+            num_inference_steps (`int`):
+                The number of diffusion steps used when generating samples with a pre-trained model. If used,
                 `timesteps` must be `None`.
-            device (`str` or `torch.device`, optional):
-                the device to which the timesteps are moved to.
-            custom_timesteps (`List[int]`, optional):
-                custom timesteps used to support arbitrary spacing between timesteps. If `None`, then the default
-                timestep spacing strategy of equal spacing between timesteps is used. If passed, `num_inference_steps`
-                must be `None`.
+            device (`str` or `torch.device`, *optional*):
+                The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
+            timesteps (`List[int]`, *optional*):
+                Custom timesteps used to support arbitrary spacing between timesteps. If `None`, then the default
+                timestep spacing strategy of equal spacing between timesteps is used. If `timesteps` is passed,
+                `num_inference_steps` must be `None`.
 
         """
         if num_inference_steps is not None and timesteps is not None:

diffusers/schedulers/scheduling_deis_multistep.py

@@ -72,63 +72,51 @@ def betas_for_alpha_bar(
 
 class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
     """
-    DEIS (https://arxiv.org/abs/2204.13902) is a fast high order solver for diffusion ODEs. We slightly modify the
-    polynomial fitting formula in log-rho space instead of the original linear t space in DEIS paper. The modification
-    enjoys closed-form coefficients for exponential multistep update instead of replying on the numerical solver. More
-    variants of DEIS can be found in https://github.com/qsh-zh/deis.
+    `DEISMultistepScheduler` is a fast high order solver for diffusion ordinary differential equations (ODEs).
 
-    Currently, we support the log-rho multistep DEIS. We recommend to use `solver_order=2 / 3` while `solver_order=1`
-    reduces to DDIM.
-
-    We also support the "dynamic thresholding" method in Imagen (https://arxiv.org/abs/2205.11487). For pixel-space
-    diffusion models, you can set `thresholding=True` to use the dynamic thresholding.
-
-    [`~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`, `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.
-        solver_order (`int`, default `2`):
-            the order of DEIS; can be `1` or `2` or `3`. We recommend to use `solver_order=2` for guided sampling, and
-            `solver_order=3` for unconditional sampling.
-        prediction_type (`str`, default `epsilon`):
-            indicates whether the model predicts the noise (epsilon), or the data / `x0`. One of `epsilon`, `sample`,
-            or `v-prediction`.
-        thresholding (`bool`, default `False`):
-            whether to use the "dynamic thresholding" method (introduced by Imagen, https://arxiv.org/abs/2205.11487).
-            Note that the thresholding method is unsuitable for latent-space diffusion models (such as
-            stable-diffusion).
-        dynamic_thresholding_ratio (`float`, default `0.995`):
-            the ratio for the dynamic thresholding method. Default is `0.995`, the same as Imagen
-            (https://arxiv.org/abs/2205.11487).
-        sample_max_value (`float`, default `1.0`):
-            the threshold value for dynamic thresholding. Valid only when `thresholding=True`
-        algorithm_type (`str`, default `deis`):
-            the algorithm type for the solver. current we support multistep deis, we will add other variants of DEIS in
-            the future
-        lower_order_final (`bool`, default `True`):
-            whether to use lower-order solvers in the final steps. Only valid for < 15 inference steps. We empirically
-            find this trick can stabilize the sampling of DEIS for steps < 15, especially for steps <= 10.
+        trained_betas (`np.ndarray`, *optional*):
+            Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`.
+        solver_order (`int`, defaults to 2):
+            The DEIS order which can be `1` or `2` or `3`. It is recommended to use `solver_order=2` for guided
+            sampling, and `solver_order=3` for unconditional sampling.
+        prediction_type (`str`, defaults to `epsilon`):
+            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).
+        thresholding (`bool`, defaults to `False`):
+            Whether to use the "dynamic thresholding" method. This is unsuitable for latent-space diffusion models such
+            as Stable Diffusion.
+        dynamic_thresholding_ratio (`float`, defaults to 0.995):
+            The ratio for the dynamic thresholding method. Valid only when `thresholding=True`.
+        sample_max_value (`float`, defaults to 1.0):
+            The threshold value for dynamic thresholding. Valid only when `thresholding=True`.
+        algorithm_type (`str`, defaults to `deis`):
+            The algorithm type for the solver.
+        lower_order_final (`bool`, defaults to `True`):
+            Whether to use lower-order solvers in the final steps. Only valid for < 15 inference steps.
         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]
@@ -201,13 +189,13 @@ class DEISMultistepScheduler(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.
         """
         # "linspace", "leading", "trailing" corresponds to annotation of Table 2. of https://arxiv.org/abs/2305.08891
         if self.config.timestep_spacing == "linspace":
@@ -296,16 +284,19 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
         self, model_output: torch.FloatTensor, timestep: int, sample: torch.FloatTensor
     ) -> torch.FloatTensor:
         """
-        Convert the model output to the corresponding type that the algorithm DEIS needs.
+        Convert the model output to the corresponding type the DEIS algorithm needs.
 
         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 the 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.
 
         Returns:
-            `torch.FloatTensor`: the converted model output.
+            `torch.FloatTensor`:
+                The converted model output.
         """
         if self.config.prediction_type == "epsilon":
             alpha_t, sigma_t = self.alpha_t[timestep], self.sigma_t[timestep]
@@ -341,14 +332,18 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
         One step for the first-order DEIS (equivalent to DDIM).
 
         Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
-            timestep (`int`): current discrete timestep in the diffusion chain.
-            prev_timestep (`int`): previous discrete timestep in the diffusion chain.
+            model_output (`torch.FloatTensor`):
+                The direct output from the learned diffusion model.
+            timestep (`int`):
+                The current discrete timestep in the diffusion chain.
+            prev_timestep (`int`):
+                The previous 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.
 
         Returns:
-            `torch.FloatTensor`: the sample tensor at the previous timestep.
+            `torch.FloatTensor`:
+                The sample tensor at the previous timestep.
         """
         lambda_t, lambda_s = self.lambda_t[prev_timestep], self.lambda_t[timestep]
         alpha_t, alpha_s = self.alpha_t[prev_timestep], self.alpha_t[timestep]
@@ -372,14 +367,17 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
 
         Args:
             model_output_list (`List[torch.FloatTensor]`):
-                direct outputs from learned diffusion model at current and latter timesteps.
-            timestep (`int`): current and latter discrete timestep in the diffusion chain.
-            prev_timestep (`int`): previous discrete timestep in the diffusion chain.
+                The direct outputs from learned diffusion model at current and latter timesteps.
+            timestep (`int`):
+                The current and latter discrete timestep in the diffusion chain.
+            prev_timestep (`int`):
+                The previous 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.
 
         Returns:
-            `torch.FloatTensor`: the sample tensor at the previous timestep.
+            `torch.FloatTensor`:
+                The sample tensor at the previous timestep.
         """
         t, s0, s1 = prev_timestep, timestep_list[-1], timestep_list[-2]
         m0, m1 = model_output_list[-1], model_output_list[-2]
@@ -414,14 +412,17 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
 
         Args:
             model_output_list (`List[torch.FloatTensor]`):
-                direct outputs from learned diffusion model at current and latter timesteps.
-            timestep (`int`): current and latter discrete timestep in the diffusion chain.
-            prev_timestep (`int`): previous discrete timestep in the diffusion chain.
+                The direct outputs from learned diffusion model at current and latter timesteps.
+            timestep (`int`):
+                The current and latter discrete timestep in the diffusion chain.
+            prev_timestep (`int`):
+                The previous 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 diffusion process.
 
         Returns:
-            `torch.FloatTensor`: the sample tensor at the previous timestep.
+            `torch.FloatTensor`:
+                The sample tensor at the previous timestep.
         """
         t, s0, s1, s2 = prev_timestep, timestep_list[-1], timestep_list[-2], timestep_list[-3]
         m0, m1, m2 = model_output_list[-1], model_output_list[-2], model_output_list[-3]
@@ -467,18 +468,23 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
-        Step function propagating the sample with the multistep DEIS.
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with
+        the multistep DEIS.
 
         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 (`float`):
+                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:
@@ -533,10 +539,12 @@ class DEISMultistepScheduler(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