Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering
This work addresses the limitation of existing models like DALL-E3 and Ideogram 1.0 in handling multilingual text in graphic design, providing a solution for users needing accurate and visually appealing text in multiple languages.
The paper tackles the problem of multilingual visual text rendering by extending Glyph-ByT5 to support 10 languages and improving aesthetic quality, resulting in Glyph-ByT5-v2 and Glyph-SDXL-v2 models that achieve accurate spelling across these languages.
Recently, Glyph-ByT5 has achieved highly accurate visual text rendering performance in graphic design images. However, it still focuses solely on English and performs relatively poorly in terms of visual appeal. In this work, we address these two fundamental limitations by presenting Glyph-ByT5-v2 and Glyph-SDXL-v2, which not only support accurate visual text rendering for 10 different languages but also achieve much better aesthetic quality. To achieve this, we make the following contributions: (i) creating a high-quality multilingual glyph-text and graphic design dataset consisting of more than 1 million glyph-text pairs and 10 million graphic design image-text pairs covering nine other languages, (ii) building a multilingual visual paragraph benchmark consisting of 1,000 prompts, with 100 for each language, to assess multilingual visual spelling accuracy, and (iii) leveraging the latest step-aware preference learning approach to enhance the visual aesthetic quality. With the combination of these techniques, we deliver a powerful customized multilingual text encoder, Glyph-ByT5-v2, and a strong aesthetic graphic generation model, Glyph-SDXL-v2, that can support accurate spelling in 10 different languages. We perceive our work as a significant advancement, considering that the latest DALL-E3 and Ideogram 1.0 still struggle with the multilingual visual text rendering task.