Research map / Image generation / Editing and style transfer
FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
Jeongsol Kim, Yeobin Hong, Jonghyun Park, Jong Chul Ye
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add terminal-point source similarity regularization (FlowAlign vs FlowEdit) | FlowEdit · PIE-Bench | background PSNR: 23.02 -> 25.50 | Improved |
| add terminal-point regularization | FlowEdit · PIE-Bench backward editing | PSNR: 19.88 -> 27.42 | Improved |
| add terminal-point regularization | FlowEdit · PIE-Bench | CLIP entire: 25.98 -> 25.28 | Hurt |
| compute CFG only for target velocity (efficient CFG) | FlowEdit · Runtime on RTX 4090 | seconds: 10.64 -> 7.14 | Improved |
| remove both guidance terms (omega=zeta=0) (ablation) | FlowAlign · PIE-Bench | editing strength | Hurt |
| set zeta=0.01 (ablation) | FlowAlign · PIE-Bench | semantic vs structure trade-off | Improved |
| use FlowAlign in place of score distillation | Gaussian splatting editing · 3D editing | qualitative | Improved |
Later papers that compared with this method
5 later accepted papers report FlowAlign as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- Target-aware Image Editing via Cycle-consistent Constraints (ECCV 2026 · better on 2 of 3 shared results)
- Multi-History-Step SDE Inversion for Image Editing with Superior Regional Awareness (ECCV 2026 · better on 3 of 3 shared results)
- V-HOLD: Stabilizing Flow Trajectories to Rethink the Edit–Preservation Trade-off (ECCV 2026 · better on 2 of 2 shared results)
- DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing (ICML 2026 · better on 1 of 1 shared result)
- Wavelet-Guided Semantic Signal Compensation for Inversion-Free Image Editing (ECCV 2026 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FlowEdit — FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models (ICCV 2025) · better on 7 of 8 shared results
- SDEdit — SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations (ICLR 2022) · better on 7 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing (CVPR 2025 · similarity 0.92)
- SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing (NeurIPS 2025 · similarity 0.91)
- Inversion-Free Image Editing with Language-Guided Diffusion Models (CVPR 2024 · similarity 0.89)
- Latent Space Editing in Transformer-Based Flow Matching (AAAI 2024 · similarity 0.89)
- EditInfinity: Image Editing with Binary-Quantized Generative Models (NeurIPS 2025 · similarity 0.88)
- DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
