STORK: Faster Diffusion And Flow Matching Sampling By Resolving Both Stiffness And Structure-Dependence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tan, Zheng, Wang, Weizhen, Bertozzi, Andrea L., Ryu, Ernest K.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914068897464320
author Tan, Zheng
Wang, Weizhen
Bertozzi, Andrea L.
Ryu, Ernest K.
author_facet Tan, Zheng
Wang, Weizhen
Bertozzi, Andrea L.
Ryu, Ernest K.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24210
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STORK: Faster Diffusion And Flow Matching Sampling By Resolving Both Stiffness And Structure-Dependence
Tan, Zheng
Wang, Weizhen
Bertozzi, Andrea L.
Ryu, Ernest K.
Computer Vision and Pattern Recognition
Numerical Analysis
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.
title STORK: Faster Diffusion And Flow Matching Sampling By Resolving Both Stiffness And Structure-Dependence
topic Computer Vision and Pattern Recognition
Numerical Analysis
url https://arxiv.org/abs/2505.24210