Towards Training-Free Scene Text Editing

TL;DR

TextFlow introduces a training-free scene text editing framework that combines attention guidance and flow modeling to enable high-quality, flexible text modifications in images without additional training, outperforming existing methods.

Contribution

It presents a novel training-free approach integrating Attention Boost and Flow Manifold Steering for effective scene text editing without task-specific training.

Findings

Achieves comparable or superior visual quality and text accuracy to training-based methods.

Generalizes well across diverse scenes and languages.

Operates in an end-to-end, plug-and-play manner.

Abstract

Scene text editing seeks to modify textual content in natural images while maintaining visual realism and semantic consistency. Existing methods often require task-specific training or paired data, limiting their scalability and adaptability. In this paper, we propose TextFlow, a training-free scene text editing framework that integrates the strengths of Attention Boost (AttnBoost) and Flow Manifold Steering (FMS) to enable flexible, high-fidelity text manipulation without additional training. Specifically, FMS preserves the structural and style consistency by modeling the visual flow of characters and background regions, while AttnBoost enhances the rendering of textual content through attention-based guidance. By jointly leveraging these complementary modules, our approach performs end-to-end text editing through semantic alignment and spatial refinement in a plug-and-play manner. Extensive experiments demonstrate that our framework achieves visual quality and text accuracy comparable to or superior to those of training-based counterparts, generalizing well across diverse scenes and languages. This study advances scene text editing toward a more efficient, generalizable, and training-free paradigm. Code is available at https://github.com/lyb18758/TextFlow