LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis

steve z, Jerry Wu, Xinyue Li, Bo Zhang, Ming Li, qinqi, Dongyang Liu (Chris Liu), KAIPENG ZHANG, Hongsheng LI, Yu Qiao, Peng Gao, Bin Fu, Zhen Li

LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis: 25 upvotes on Hugging Face Daily Papers, #6 of 22 papers on 2025-03-28. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.