STORK: Faster Diffusion And Flow Matching Sampling By Resolving Both Stiffness And Structure-Dependence
This work provides a faster sampling method for diffusion and flow-matching models, which is incremental as it builds on prior training-free approaches to overcome specific limitations.
The paper tackles the problem of slow sampling in diffusion and flow-matching models by introducing STORK, a method that addresses stiffness and structure-dependence, resulting in improved quality for image and video generation with fewer function evaluations.
Diffusion models (DMs) and flow-matching models have demonstrated remarkable performance in image and video generation. However, such models require a significant number of function evaluations (NFEs) during sampling, leading to costly inference. Consequently, quality-preserving fast sampling methods that require fewer NFEs have been an active area of research. However, prior training-free sampling methods fail to simultaneously address two key challenges: the stiffness of the ODE (i.e., the non-straightness of the velocity field) and dependence on the semi-linear structure of the DM ODE (which limits their direct applicability to flow-matching models). In this work, we introduce the Stabilized Taylor Orthogonal Runge--Kutta (STORK) method, addressing both design concerns. We demonstrate that STORK consistently improves the quality of diffusion and flow-matching sampling for image and video generation. Code is available at https://github.com/ZT220501/STORK.