EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (9) · 7565-7573
DOI: 10.1609/aaai.v40i9.37697 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Runnan Lu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref).
Abstract (Originalsprache)
Generating accurate multilingual text with diffusion models has long been desired but remains challenging. Recent methods have made progress in rendering text in a single language, but rendering arbitrary languages is still an under-explored area. This paper introduces EasyText, a text rendering framework based on DiT (Diffusion Transformer), which connects denoising latents with multilingual character tokens encoded as character tokens. We propose character positioning encoding and position encoding interpolation techniques to achieve controllable and precise text rendering. Additionally, we construct a large-scale synthetic text image dataset with 1 million multilingual image-text annotations as well as a high-quality dataset of 20K annotated images, which are used for pretraining and fine-tuning respectively. Extensive experiments and evaluations demonstrate the effectiveness and advancement of our approach in multilingual text rendering, visual quality, and layout-aware text integration.
Zitieren
APA
Lu, R., Zhang, Y., Liu, J., Wang, H., & Song, Y. (2026). EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering. Proceedings of the AAAI Conference on Artificial Intelligence, 40(9), 7565-7573. https://doi.org/10.1609/aaai.v40i9.37697
Vancouver
Lu R, Zhang Y, Liu J, Wang H, Song Y. EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(9):7565-7573. doi:10.1609/aaai.v40i9.37697
BibTeX
@article{Lu2026,
author = {Lu, Runnan and Zhang, Yuxuan and Liu, Jiaming and Wang, Haofan and Song, Yiren},
title = {EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {9},
pages = {7565--7573},
doi = {10.1609/aaai.v40i9.37697}
}
EUVIMED