Taming Rectified Flow for Inversion and Editing

Jiangshan Wang; Junfu Pu; Zhongang Qi; Jiayi Guo; Yue Ma; Nisha Huang; Yuxin Chen; Xiu Li; Ying Shan

doi:10.48550/arxiv.2411.04746

ICML2025顶会

Taming Rectified Flow for Inversion and Editing

Jiangshan Wang, Junfu Pu, Zhongang Qi, Jiayi Guo, Yue Ma, Nisha Huang, Yuxin Chen, Xiu Li, Ying Shan

arXiv DOI 出版方

2025年份

95顶会引用

摘要

Rectified-flow-based diffusion transformers like FLUX and OpenSora have demonstrated outstanding performance in the field of image and video generation. Despite their robust generative capabilities, these models often struggle with inversion inaccuracies, which could further limit their effectiveness in downstream tasks such as image and video editing. To address this issue, we * Equal contribution