AI Paper Atlas

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

TextMaster: A Unified Framework for Realistic Text Editing via Glyph-Style Dual-Control

Zhenyu Yan, Jian Wang, Aoqiang Wang, Yuhan Li, Wenxiang Shang, Zhu Hangcheng

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 4 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 token-separated text encoder (ablation)TextMaster (cumulative) · Ablation (500 images)OCR accuracy: 0.5098 -> 0.6832Improved
add token-separated text encoder (ablation)TextMaster (cumulative) · Ablation (500 images)FID: 16.26 -> 14.58Improved
add perceptual loss (ablation)TextMaster (cumulative) · Ablation (500 images)OCR accuracy: 0.6832 -> 0.7451Improved
add perceptual loss (ablation)TextMaster (cumulative) · Ablation (500 images)FID: 14.58 -> 12.95Improved
add attention IoU loss (ablation)TextMaster (cumulative) · Ablation (500 images)NED: 0.7638 -> 0.8495Improved
add attention IoU loss (ablation)TextMaster (cumulative) · Ablation (500 images)FID: 12.95 -> 13.02No clear effect
add in-context reference (ablation)TextMaster (cumulative) · Ablation (500 images)OCR accuracy: 0.7816 -> 0.8162Improved
add in-context reference (ablation)TextMaster (cumulative) · Ablation (500 images)FID: 13.02 -> 11.65Improved
add style adapter (ablation)TextMaster (cumulative) · Ablation (500 images)OCR accuracy: 0.8162 -> 0.8860Improved
add style adapter (ablation)TextMaster (cumulative) · Ablation (500 images)LPIPS: 0.0338 -> 0.0286Improved
use TextMaster instead of TextCtrlTextMaster · AnyText-Benchmark EnglishFID: 6.01 -> 10.35Hurt
use TextMaster instead of AnyText2TextMaster · AnyText-Benchmark ChineseOCR accuracy: 0.6133 -> 0.9257Improved

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