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

class diffusers.DPMSolverSDEScheduler

( *args**kwargs )

SchedulerOutput

class diffusers.schedulers.scheduling_utils.SchedulerOutput

( prev_sample: Tensor )

パラメータ

prev_sample（画像の場合、torch.Tensor、形状 (batch_size, num_channels, height, width)） — 前のタイムステップの計算済みサンプル (x_{t-1})。prev_sample は、デノイジングループにおける次のモデル入力として使用します。

スケジューラーのstep関数の出力の基底クラス。

Update on GitHub

←DPMSolverMultistepScheduler DPMSolverSinglestepScheduler→