AI Paper Atlas

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

InnoText: A Unified Model for Visual Text Generation and Editing

Haowei Liu, Runze He, Jian Lu, Ao Ma, Run Ling, Ke Cao, Jiasong Feng, Wei Feng, Shuo Lu, Yexing Xu, WANG Yun, Jing Wang and 1 more

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 2 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 Font Size-Aware Modulation (FSAM) (ablation)InnoText · InnoText-Bench generationLPIPS: 0.5928 -> 0.5311Improved
add FSAM (ablation)InnoText · InnoText-Bench editingSen. Acc: 0.5672 -> 0.6374Improved
add Small-Character Aware Augmentation (ablation)InnoText · InnoText-Bench editingSen. Acc: 0.5963 -> 0.6374Improved
add Task-Specific Region Weighted Loss (ablation)InnoText · InnoText-Bench editingSen. Acc: 0.6180 -> 0.6374Improved
add Task-Specific Region Weighted Loss (ablation)InnoText · InnoText-Bench editingNED: 0.7533 -> 0.7528No clear effect
fine-tune AnyText2 on InnoText-30K (ablation)AnyText2 · InnoText-BenchSen. Acc: edit 0.5882, gen 0.5358 vs InnoText 0.6374 / 0.5907Mixed
train on AnyWord-3M instead of InnoText-30KInnoText · AnyText-Benchmark editing (English)Sen. Acc: 0.7988 -> 0.8224Improved
increase LoRA rank from 32 to 128 (ablation)InnoText · InnoText-BenchSen. Acc: 0.5902 -> 0.6586Improved
increase LoRA rank from 128 to 256 (ablation)InnoText · InnoText-Bench generationSen. Acc: 0.5907 -> 0.5889No clear effect
unified model vs TextFlux on generationInnoText · InnoText-Bench generationSen. Acc: 0.0071 -> 0.6586Improved

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