FlowBypass: Rectified Flow Trajectory Bypass for Training-Free Image Editing
Menglin Han, Zhangkai Ni

TL;DR
FlowBypass introduces a training-free image editing method that constructs a direct trajectory bypass to improve prompt alignment and detail preservation without relying on feature manipulations.
Contribution
It proposes a novel Rectified Flow-based framework that constructs a direct bypass between inversion and reconstruction trajectories, enhancing editing performance.
Findings
Outperforms state-of-the-art methods in prompt alignment
Preserves high-fidelity details in irrelevant regions
Mitigates error accumulation in trajectory-based editing
Abstract
Training-free image editing has attracted increasing attention for its efficiency and independence from training data. However, existing approaches predominantly rely on inversion-reconstruction trajectories, which impose an inherent trade-off: longer trajectories accumulate errors and compromise fidelity, while shorter ones fail to ensure sufficient alignment with the edit prompt. Previous attempts to address this issue typically employ backbone-specific feature manipulations, limiting general applicability. To address these challenges, we propose FlowBypass, a novel and analytical framework grounded in Rectified Flow that constructs a bypass directly connecting inversion and reconstruction trajectories, thereby mitigating error accumulation without relying on feature manipulations. We provide a formal derivation of two trajectories, from which we obtain an approximate bypass…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Cell Image Analysis Techniques · Advanced Vision and Imaging
