Type-R: Automatically Retouching Typos for Text-to-Image Generation
This addresses a specific limitation in text-to-image generation for applications requiring accurate textual content, representing an incremental improvement over existing methods.
The paper tackles the problem of inaccurate text rendering in text-to-image models by proposing Type-R, a post-processing method that identifies and corrects typographical errors in generated images. The approach achieves the highest text rendering accuracy while maintaining image quality when combined with models like Stable Diffusion or Flux.
While recent text-to-image models can generate photorealistic images from text prompts that reflect detailed instructions, they still face significant challenges in accurately rendering words in the image. In this paper, we propose to retouch erroneous text renderings in the post-processing pipeline. Our approach, called Type-R, identifies typographical errors in the generated image, erases the erroneous text, regenerates text boxes for missing words, and finally corrects typos in the rendered words. Through extensive experiments, we show that Type-R, in combination with the latest text-to-image models such as Stable Diffusion or Flux, achieves the highest text rendering accuracy while maintaining image quality and also outperforms text-focused generation baselines in terms of balancing text accuracy and image quality.