SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models

TL;DR

SA-Solver is a novel stochastic Adams method that accelerates diffusion model sampling, achieving high-quality data generation with fewer steps and state-of-the-art FID scores on benchmark datasets.

Contribution

The paper introduces SA-Solver, an efficient stochastic Adams method for diffusion SDEs, improving sampling speed and quality over existing techniques.

Findings

Achieves comparable or better performance than SOTA sampling methods.

Attains state-of-the-art FID scores with fewer function evaluations.

Provides a comprehensive analysis of stochastic diffusion sampling methods.

Abstract

Diffusion Probabilistic Models (DPMs) have achieved considerable success in generation tasks. As sampling from DPMs is equivalent to solving diffusion SDE or ODE which is time-consuming, numerous fast sampling methods built upon improved differential equation solvers are proposed. The majority of such techniques consider solving the diffusion ODE due to its superior efficiency. However, stochastic sampling could offer additional advantages in generating diverse and high-quality data. In this work, we engage in a comprehensive analysis of stochastic sampling from two aspects: variance-controlled diffusion SDE and linear multi-step SDE solver. Based on our analysis, we propose \textit{SA-Solver}, which is an improved efficient stochastic Adams method for solving diffusion SDE to generate data with high quality. Our experiments show that \textit{SA-Solver} achieves: 1) improved or comparable performance compared with the existing state-of-the-art (SOTA) sampling methods for few-step sampling; 2) SOTA FID on substantial benchmark datasets under a suitable number of function evaluations (NFEs). Code is available at https://github.com/scxue/SA-Solver.