LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis
Shitian Zhao, Qilong Wu, Xinyue Li, Bo Zhang, Ming Li, Qi Qin, Dongyang Liu, Kaipeng Zhang, Hongsheng Li, Yu Qiao, Peng Gao, Bin Fu, Zhen Li
2025-03-28
Summary
This paper is about creating a better way to generate images with clear and high-quality text in them.
What's the problem?
It's hard to create images where the text looks good and matches what the image is supposed to be about.
What's the solution?
The researchers created a system that uses high-quality training data and special AI models to generate images with realistic-looking text.
Why it matters?
This work matters because it can help create more realistic and visually appealing images with text, which is useful for things like graphic design and advertising.
Abstract
We introduce LeX-Art, a comprehensive suite for high-quality text-image synthesis that systematically bridges the gap between prompt expressiveness and text rendering fidelity. Our approach follows a data-centric paradigm, constructing a high-quality data synthesis pipeline based on Deepseek-R1 to curate LeX-10K, a dataset of 10K high-resolution, aesthetically refined 1024times1024 images. Beyond dataset construction, we develop LeX-Enhancer, a robust prompt enrichment model, and train two text-to-image models, LeX-FLUX and LeX-Lumina, achieving state-of-the-art text rendering performance. To systematically evaluate visual text generation, we introduce LeX-Bench, a benchmark that assesses fidelity, aesthetics, and alignment, complemented by Pairwise Normalized Edit Distance (PNED), a novel metric for robust text accuracy evaluation. Experiments demonstrate significant improvements, with LeX-Lumina achieving a 79.81% PNED gain on CreateBench, and LeX-FLUX outperforming baselines in color (+3.18%), positional (+4.45%), and font accuracy (+3.81%). Our codes, models, datasets, and demo are publicly available.