AI Paper Atlas

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

Towards Training-free Scene Text Editing

Yubo Li, Xugong Qin, Peng Zhang, Hailun Lin, Gangyan Zeng, Kexin Zhang

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 1 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
add FMS module to the editing pipeline (ablation)TextFlow (FLUX-Kontext) · ScenePairPSNR: 20.47 -> 22.42Improved
add FMS module to the editing pipeline (ablation)TextFlow (FLUX-Kontext) · ScenePairFID: 16.69 -> 13.52Improved
add AttnBoost to the editing pipeline (ablation)TextFlow (FLUX-Kontext) · ScenePairACC (%): 20.35 -> 79.80Improved
add AttnBoost to the editing pipeline (ablation)TextFlow (FLUX-Kontext) · ScenePair (Random)ACC (%): 18.84 -> 74.52Improved
TextFlow vs plain FLUX-Kontext baselineFLUX-Kontext · ScenePair (Random)ACC (%): 76.63 -> 74.52Hurt
use Overshoot scheduler instead of Euler (ablation)TextFlow · ScenePairACC (%): 78.73 -> 79.90Improved
increase denoising steps from 50 to 70 (ablation)TextFlow · ScenePairFID: 13.53 -> 12.83No clear effect
increase denoising steps from 24 to 50 (ablation)TextFlow · ScenePairACC (%): 77.97 -> 79.98Improved
use TextFlow instead of training-based TextFluxTextFlow vs TextFlux · ScenePairACC (%): 80.40 -> 79.98 ACC; FID 54.64 -> 13.53Mixed

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