TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis

TL;DR

TextFlux is a novel OCR-free diffusion-based model for high-fidelity, multilingual scene text synthesis that requires less data and offers flexible, controllable multi-line text generation.

Contribution

It introduces TextFlux, a DiT-based framework that eliminates OCR modules, enhances multilingual scalability, reduces training data needs, and enables precise multi-line text control.

Findings

Outperforms previous methods in qualitative evaluations.

Effective in low-resource multilingual settings.

Requires only 1% of the training data compared to competitors.

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 (additional visual conditioning modules) 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.