TextAtlas5M: A Large-Scale Dataset for Long Text Image Generation
Dongxing Mao, Alex Jinpeng Wang, weiming Han, Jiawei Zhang, Zhuobai Dong, Linjie Li, Lin Yiqi, Zhengyuan Yang
Abstract
Text-conditioned image generation has made rapid progress, yet rendering images with long-form text remains challenging due to the limitations of existing datasets, which predominantly focus on short and simple text. We introduce TextAtlas5M, a large-scale dataset designed to evaluate long-text rendering, where “long text” encompasses not only textual length but also layout complexity and semantic richness. TextAtlas5M contains 5 million generated and collected images across diverse data types, enabling comprehensive evaluation of large-scale generative models. We further curate 4,000 human-improved test cases (TextAtlasEval) spanning four domains, forming one of the most extensive benchmarks for text rendering. Evaluations show that TextAtlas5M poses substantial challenges even for state-of-the-art proprietary models (e.g., GPT-4o), with significantly larger gaps observed for open-source models. Training on TextAtlas5M consistently improves text rendering for both diffusion-based and autoregressive models, demonstrating its effectiveness for advancing text-rich image generation.
BibTeX
@inproceedings{
mao2026textatlasm,
title={TextAtlas5M: A Large-Scale Dataset for Long Text Image Generation},
author={Dongxing Mao and Alex Jinpeng Wang and Weiming Han and Jiawei Zhang and Zhuobai Dong and Linjie Li and Yiqi Lin and Zhengyuan Yang and Libo Qin and Fuwei Zhang and Lijuan Wang and Min Li},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=5vufrrbi4N}
}