Hugging Face's logo

Diffusers documentation

CosineDPMSolverMultistepScheduler

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

CosineDPMSolverMultistepScheduler

The CosineDPMSolverMultistepScheduler is a variant of DPMSolverMultistepScheduler with cosine schedule, proposed by Nichol and Dhariwal (2021). It is being used in the Stable Audio Open paper and the Stability-AI/stable-audio-tool codebase.

This scheduler was contributed by Yoach Lacombe.

CosineDPMSolverMultistepScheduler

class diffusers.CosineDPMSolverMultistepScheduler

< >

( sigma_min: float = 0.3 sigma_max: float = 500 sigma_data: float = 1.0 sigma_schedule: str = 'exponential' num_train_timesteps: int = 1000 solver_order: int = 2 prediction_type: str = 'v_prediction' rho: float = 7.0 solver_type: str = 'midpoint' lower_order_final: bool = True euler_at_final: bool = False final_sigmas_type: typing.Optional[str] = 'zero' )

Parameters

  • sigma_min (float, optional, defaults to 0.3) — Minimum noise magnitude in the sigma schedule. This was set to 0.3 in Stable Audio Open [1].
  • sigma_max (float, optional, defaults to 500) — Maximum noise magnitude in the sigma schedule. This was set to 500 in Stable Audio Open [1].
  • sigma_data (float, optional, defaults to 1.0) — The standard deviation of the data distribution. This is set to 1.0 in Stable Audio Open [1].
  • sigma_schedule (str, optional, defaults to exponential) — Sigma schedule to compute the sigmas. By default, we the schedule introduced in the EDM paper (https://arxiv.org/abs/2206.00364). Other acceptable value is “exponential”. The exponential schedule was incorporated in this model: https://huggingface.co./stabilityai/cosxl.
  • num_train_timesteps (int, defaults to 1000) — The number of diffusion steps to train the model.
  • solver_order (int, defaults to 2) — The DPMSolver order which can be 1 or 2. It is recommended to use solver_order=2.
  • prediction_type (str, defaults to v_prediction, 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 paper).
  • solver_type (str, defaults to midpoint) — Solver type for the second-order solver; can be midpoint or heun. The solver type slightly affects the sample quality, especially for a small number of steps. It is recommended to use midpoint solvers.
  • lower_order_final (bool, defaults to True) — Whether to use lower-order solvers in the final steps. Only valid for < 15 inference steps. This can stabilize the sampling of DPMSolver for steps < 15, especially for steps <= 10.
  • euler_at_final (bool, defaults to False) — Whether to use Euler’s method in the final step. It is a trade-off between numerical stability and detail richness. This can stabilize the sampling of the SDE variant of DPMSolver for small number of inference steps, but sometimes may result in blurring.
  • final_sigmas_type (str, defaults to "zero") — The final sigma value for the noise schedule during the sampling process. If "sigma_min", the final sigma is the same as the last sigma in the training schedule. If zero, the final sigma is set to 0.

Implements a variant of DPMSolverMultistepScheduler with cosine schedule, proposed by Nichol and Dhariwal (2021). This scheduler was used in Stable Audio Open [1].

[1] Evans, Parker, et al. “Stable Audio Open” https://arxiv.org/abs/2407.14358

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.

convert_model_output

< >

( model_output: Tensor sample: Tensor = None ) → torch.Tensor

Parameters

  • model_output (torch.Tensor) — The direct output from the learned diffusion model.
  • sample (torch.Tensor) — A current instance of a sample created by the diffusion process.

Returns

torch.Tensor

The converted model output.

Convert the model output to the corresponding type the DPMSolver/DPMSolver++ algorithm needs. DPM-Solver is designed to discretize an integral of the noise prediction model, and DPM-Solver++ is designed to discretize an integral of the data prediction model.

The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise prediction and data prediction models.

dpm_solver_first_order_update

< >

( model_output: Tensor sample: Tensor = None noise: typing.Optional[torch.Tensor] = None ) → torch.Tensor

Parameters

  • model_output (torch.Tensor) — The direct output from the learned diffusion model.
  • sample (torch.Tensor) — A current instance of a sample created by the diffusion process.

Returns

torch.Tensor

The sample tensor at the previous timestep.

One step for the first-order DPMSolver (equivalent to DDIM).

multistep_dpm_solver_second_order_update

< >

( model_output_list: typing.List[torch.Tensor] sample: Tensor = None noise: typing.Optional[torch.Tensor] = None ) → torch.Tensor

Parameters

  • model_output_list (List[torch.Tensor]) — The direct outputs from learned diffusion model at current and latter timesteps.
  • sample (torch.Tensor) — A current instance of a sample created by the diffusion process.

Returns

torch.Tensor

The sample tensor at the previous timestep.

One step for the second-order multistep DPMSolver.

scale_model_input

< >

( sample: Tensor timestep: typing.Union[float, torch.Tensor] ) → torch.Tensor

Parameters

  • sample (torch.Tensor) — The input sample.
  • timestep (int, optional) — The current timestep in the diffusion chain.

Returns

torch.Tensor

A scaled input sample.

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.

set_begin_index

< >

( begin_index: int = 0 )

Parameters

  • begin_index (int) — The begin index for the scheduler.

Sets the begin index for the scheduler. This function should be run from pipeline before the inference.

set_timesteps

< >

( num_inference_steps: int = None device: typing.Union[str, torch.device] = None )

Parameters

  • 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.

Sets the discrete timesteps used for the diffusion chain (to be run before inference).

step

< >

( model_output: Tensor timestep: typing.Union[int, torch.Tensor] sample: Tensor generator = None return_dict: bool = True ) → SchedulerOutput or tuple

Parameters

  • model_output (torch.Tensor) — The direct output from learned diffusion model.
  • timestep (int) — The current discrete timestep in the diffusion chain.
  • sample (torch.Tensor) — 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 SchedulerOutput or tuple.

Returns

SchedulerOutput or tuple

If return_dict is True, SchedulerOutput is returned, otherwise a tuple is returned where the first element is the sample tensor.

Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with the multistep DPMSolver.

SchedulerOutput

class diffusers.schedulers.scheduling_utils.SchedulerOutput

< >

( prev_sample: Tensor )

Parameters

  • prev_sample (torch.Tensor 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 denoising loop.

Base class for the output of a scheduler’s step function.

< > Update on GitHub

←ConsistencyDecoderScheduler DDIMInverseScheduler→