DPMSolverSDEScheduler
The DPMSolverSDEScheduler
is inspired by the stochastic sampler from the Elucidating the Design Space of Diffusion-Based Generative Models paper, and the scheduler is ported from and created by Katherine Crowson.
DPMSolverSDEScheduler
class diffusers.DPMSolverSDEScheduler
< source >( num_train_timesteps: int = 1000 beta_start: float = 0.00085 beta_end: float = 0.012 beta_schedule: str = 'linear' trained_betas: Union = None prediction_type: str = 'epsilon' use_karras_sigmas: Optional = False use_exponential_sigmas: Optional = False use_beta_sigmas: Optional = False noise_sampler_seed: Optional = None timestep_spacing: str = 'linspace' steps_offset: int = 0 )
Parameters
- num_train_timesteps (
int
, defaults to 1000) — The number of diffusion steps to train the model. - beta_start (
float
, defaults to 0.00085) — The startingbeta
value of inference. - beta_end (
float
, defaults to 0.012) — The finalbeta
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 fromlinear
orscaled_linear
. - trained_betas (
np.ndarray
, optional) — Pass an array of betas directly to the constructor to bypassbeta_start
andbeta_end
. - prediction_type (
str
, defaults toepsilon
, optional) — Prediction type of the scheduler function; can beepsilon
(predicts the noise of the diffusion process),sample
(directly predicts the noisy sample) or
v_prediction` (see section 2.4 of Imagen Video paper). - use_karras_sigmas (
bool
, optional, defaults toFalse
) — Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. IfTrue
, the sigmas are determined according to a sequence of noise levels {σi}. - use_exponential_sigmas (
bool
, optional, defaults toFalse
) — Whether to use exponential sigmas for step sizes in the noise schedule during the sampling process. - use_beta_sigmas (
bool
, optional, defaults toFalse
) — Whether to use beta sigmas for step sizes in the noise schedule during the sampling process. Refer to Beta Sampling is All You Need for more information. - noise_sampler_seed (
int
, optional, defaults toNone
) — The random seed to use for the noise sampler. IfNone
, a random seed is generated. - 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 for more information. - steps_offset (
int
, defaults to 0) — An offset added to the inference steps, as required by some model families.
DPMSolverSDEScheduler implements the stochastic sampler from the Elucidating the Design Space of Diffusion-Based Generative Models paper.
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.
scale_model_input
< source >( sample: Tensor timestep: Union ) → torch.Tensor
Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep.
set_begin_index
< source >( begin_index: int = 0 )
Sets the begin index for the scheduler. This function should be run from pipeline before the inference.
set_timesteps
< source >( num_inference_steps: int device: Union = None num_train_timesteps: Optional = None )
Sets the discrete timesteps used for the diffusion chain (to be run before inference).
step
< source >( model_output: Union timestep: Union sample: Union return_dict: bool = True s_noise: float = 1.0 ) → DPMSolverSDESchedulerOutput
or tuple
Parameters
- model_output (
torch.Tensor
ornp.ndarray
) — The direct output from learned diffusion model. - timestep (
float
ortorch.Tensor
) — The current discrete timestep in the diffusion chain. - sample (
torch.Tensor
ornp.ndarray
) — A current instance of a sample created by the diffusion process. - return_dict (
bool
) — Whether or not to return aDPMSolverSDESchedulerOutput
or tuple. - s_noise (
float
, optional, defaults to 1.0) — Scaling factor for noise added to the sample.
Returns
DPMSolverSDESchedulerOutput
or tuple
If return_dict is True
, DPMSolverSDESchedulerOutput
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 diffusion process from the learned model outputs (most often the predicted noise).
SchedulerOutput
class diffusers.schedulers.scheduling_utils.SchedulerOutput
< source >( prev_sample: Tensor )
Base class for the output of a scheduler’s step
function.