SyncAI.news, a Varaisys broadcasting
DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decoupling
ZZ

Zheyuan Zhan, Can Wang, Jiawei Chen, Chun Chen, Siwei Lyu, Zeyu Zheng, Defang Chen

· 1 min read

ResearcharXiv cs.CV

DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decoupling

arXiv:2609.34237v1 Announce Type: new Abstract: Flow-based image editing (FlowEdit) enables inversion-free semantic changes through the difference between source and target velocities. In this paper, we observe that FlowEdit's default classifier-free guidance (CFG) configuration, with asymmetric source and target scales, causes substantial background leakage. Matching these guidance scales, for example by removing CFG, improves edit-relevant localization but severely degrades editability. To get the best of both worlds, we propose DecFlowEdit, which decouples the optimal guidance scales for localization and for editing in flow-based generative models. In particular, DecFlowEdit first extracts an edit-relevant prior by temporally aggregating velocity differences evaluated without CFG, and then uses this prior to reweight the original updates under default CFG. Our method remains training-free and inversion-free, requiring neither external spatial masks nor attention manipulation. Experiments on PIE-Bench across FLUX, SD3, and SD3.5 show that DecFlowEdit improves background preservation, reducing structure distance by approximately 61 to 73 percent and background LPIPS by 68 to 80 percent relative to FlowEdit at comparable editing fidelity.

Original source

This story was published by arXiv cs.CV and written by Zheyuan Zhan, Can Wang, Jiawei Chen, Chun Chen, Siwei Lyu, Zeyu Zheng, Defang Chen. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News