AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models

Vladimir Kulikov, Matan Kleiner, Inbar Huberman-Spiegelglas, Tomer Michaeli

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 134 citations (OpenAlex)

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 changedWhereMeasuredEffect
edit with FlowEdit direct ODE instead of editing by inversionSD3 · Cat-to-doglatent MSE: 2239 -> 1376Improved
edit with FlowEdit instead of inversionSD3 · Cat-to-dogLPIPS: 0.25 -> 0.15Improved
edit with FlowEdit instead of inversionSD3 · Cat-to-dogFID: 55.88 -> 51.14Improved
edit with FlowEdit instead of inversionSD3 · Cat-to-dogKID: 0.023 -> 0.017Improved
FlowEdit instead of ODE inversion on SD3 datasetSD3 · Image editing datasetLPIPS: 0.318 -> 0.181Improved
FlowEdit instead of ODE inversion on FLUX datasetFLUX · Image editing datasetLPIPS: 0.374 -> 0.223Improved
FlowEdit instead of ODE inversion on FLUXFLUX · Image editing datasetCLIP-T: 0.341 -> 0.337Hurt
provide a ChatGPT-varied source prompt (ablation)FlowEdit · Source prompt ablationDINO: 0.719 -> 0.713No clear effect
remove the source prompt (empty prompt) (ablation)FlowEdit · Source prompt ablationLPIPS: 0.181 -> 0.192No clear effect
increase n_avg from 1 toward 10 (ablation)FlowEdit · SD3LPIPSImproved
deviate from the exact step size dt in the update (ablation)FlowEdit · editingqualityHurt

Later papers that compared with this method

29 later accepted papers report FlowEdit as a baseline in their results tables; 28 of them report a better number on most of the results they share with it.

21 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy