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

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)
 

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

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: