TextFlux: An OCR‐Free DiT Model for High‐Fidelity Multilingual Scene Text Synthesis
Top Cited Papers
- 27 March 2026
- journal article
- Published by Wiley in Computer Graphics Forum
Abstract
Diffusion‐based scene text synthesis has progressed rapidly, yet existing methods commonly rely on additional visual conditioning modules and require large‐scale annotated data to support multilingual generation. In this work, we revisit the necessity of complex auxiliary modules and further explore an approach that simultaneously ensures glyph accuracy and achieves high‐fidelity scene integration, by leveraging diffusion models' inherent capabilities for contextual reasoning. To this end, we introduce TextFlux, a DiT‐based framework that enables multilingual scene text synthesis. The advantages of TextFlux can be summarized as follows: (1) OCR‐free model architecture. TextFlux eliminates the need for OCR encoders that are specifically used to extract visual text‐related features. (2) Strong multilingual scalability. TextFlux is effective in low‐resource multilingual settings, and achieves strong performance in newly added languages with fewer than 1,000 samples. (3) Streamlined training setup. TextFlux is trained with only 1% of the training data required by competing methods. (4) Controllable multi‐line text generation. TextFlux offers flexible multi‐line synthesis with precise line‐level control, outperforming methods restricted to single‐line or rigid layouts. Extensive experiments and visualizations demonstrate that TextFlux outperforms previous methods in both qualitative and quantitative evaluations. Our code is available at https://github.com/yyyyyxie/textflux .Keywords
This publication has 15 references indexed in Scilit:
- POSTA: A Go-to Framework for Customized Artistic Poster Generation2025
- PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering2025
- GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing2025
- HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models2024
- Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation2024
- DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting2023
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation2023
- InstructPix2Pix: Learning to Follow Image Editing Instructions2023
- StyleFormer: Real-time Arbitrary Style Transfer via Parametric Style Composition2021
- Total-Text: toward orientation robustness in scene text detectionInternational Journal on Document Analysis and Recognition (IJDAR), 2019