# Elucidating the solution space of extended reverse-time SDE for diffusion models

Source: [Elucidating the solution space of extended reverse-time SDE for diffusion models](<https://www.sota2.com/research/paper/68fa772b1e209131cea718c3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:11:54.790Z

Authors: Qinpeng Cui, Xinyi Zhang, Qiqi Bao, Qingmin Liao

Published: 2023-09-12T12:27:17.000Z

## Abstract

Sampling from Diffusion Models can alternatively be seen as solving differential equations, where there is a challenge in balancing speed and image visual quality. ODE-based samplers offer rapid sampling time but reach a performance limit, whereas SDE-based samplers achieve superior quality, albeit with longer iterations. In this work, we formulate the sampling process as an Extended Reverse-Time SDE (ER SDE), unifying prior explorations into ODEs and SDEs. Theoretically, leveraging the semi-linear structure of ER SDE solutions, we offer exact solutions and approximate solutions for VP SDE and VE SDE, respectively. Based on the approximate solution space of the ER SDE, referred to as one-step prediction errors, we yield mathematical insights elucidating the rapid sampling capability of ODE solvers and the high-quality sampling ability of SDE solvers. Additionally, we unveil that VP SDE solvers stand on par with their VE SDE counterparts. Based on these findings, leveraging the dual advantages of ODE solvers and SDE solvers, we devise efficient high-quality samplers, namely ER-SDE-Solvers. Experimental results demonstrate that ER-SDE-Solvers achieve state-of-the-art performance across all stochastic samplers while maintaining efficiency of deterministic samplers. Specifically, on the ImageNet $128\\times128$ dataset, ER-SDE-Solvers obtain 8.33 FID in only 20 function evaluations. Code is available at \\href{https://github.com/QinpengCui/ER-SDE-Solver}{https://github.com/QinpengCui/ER-SDE-Solver}

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2309.06169>)

[PDF](<https://arxiv.org/pdf/2309.06169.pdf>)
