---
title: README
emoji: 📈
colorFrom: blue
colorTo: red
sdk: static
pinned: false
---


📰 **[Feb 2025]**

We release TextAtlas5M, a dataset specifically designed for training and evaluating multimodal generation models on dense-text image generation.

[Paper](https://arxiv.org/pdf/2502.07870) [GitHub](https://github.com/CSU-JPG/TextAtlas) [Website](https://textatlas5m.github.io)