Diffusers documentation

DPMSolverSDEScheduler

Diffusers

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

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

클래스 diffusers.DPMSolverSDEScheduler

( *args**kwargs )

SchedulerOutput

class diffusers.schedulers.scheduling_utils.SchedulerOutput

( prev_sample: Tensor )

매개변수

prev_sample (이미지의 경우 torch.Tensor, shape (batch_size, num_channels, height, width)) — 이전 timestep의 계산된 샘플 (x_{t-1}). prev_sample은 denoising 루프에서 다음 모델 입력으로 사용해야 합니다.

스케줄러의 step 함수 출력을 위한 베이스 클래스.

Update on GitHub

←DPMSolverMultistepScheduler DPMSolverSinglestepScheduler→