FlowBypass: Rectified Flow Trajectory Bypass for Training-Free Image Editing
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918318914404352 |
|---|---|
| author | Han, Menglin Ni, Zhangkai |
| author_facet | Han, Menglin Ni, Zhangkai |
| contents | 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 formulation and its numerical solution, enabling seamless trajectory transitions. Extensive experiments demonstrate that FlowBypass consistently outperforms state-of-the-art image editing methods, achieving stronger prompt alignment while preserving high-fidelity details in irrelevant regions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01805 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FlowBypass: Rectified Flow Trajectory Bypass for Training-Free Image Editing Han, Menglin Ni, Zhangkai Computer Vision and Pattern Recognition 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 formulation and its numerical solution, enabling seamless trajectory transitions. Extensive experiments demonstrate that FlowBypass consistently outperforms state-of-the-art image editing methods, achieving stronger prompt alignment while preserving high-fidelity details in irrelevant regions. |
| title | FlowBypass: Rectified Flow Trajectory Bypass for Training-Free Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.01805 |