STORK: Faster Diffusion and Flow Matching Sampling by Resolving both Stiffness and Structure-Dependence

ICLR 2026 Conference Submission14840 Authors

Keywords: diffusion model, fast sampling method, stabilized Runge--Kutta, training-free

TL;DR: We propose a new training-free fast sampler for diffusion models by resolving both stiffness and structure-dependence.

Abstract: 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.

Primary Area: generative models

Submission Number: 14840