MMODELYST
Papers/Stable and Near-Reversible Diffusion ODE Solvers for Image Editing
PAP

Stable and Near-Reversible Diffusion ODE Solvers for Image Editing

May 12, 2026

arXiv
Abstract

The inversion of diffusion models plays a central role in image editing. Algebraically reversible ODE solvers provide an appealing approach to diffusion inversion for text-guided image editing, by eliminating the inversion error inherent in DDIM-based editing pipelines. However, empirical results indicate that reversibility alone is insufficient. As edits require larger semantic or visual changes, reversible diffusion solvers often exhibit instabilities and suffer sharp drops in output quality. In this paper, we show that the trade-off between exact reversibility and numerical stability manifests empirically as a trade-off between background preservation and prompt alignment in image editing. We then investigate the use of near-reversible Runge-Kutta methods as a more stable alternative to exactly reversible diffusion schemes. When combined with a vector-field smoothing strategy, the resulting approach improves edit fidelity, remains stable under large edits, and largely retains the background-preservation benefits of reversible solvers.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Barbora Barancikova, Daniil Shmelev, Cristopher Salvi
Your notes (browser-local)
saved
arXiv:2605.16399