Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering
This addresses a fundamental challenge in text-to-image generation for applications like design and scene text rendering, representing a strong specific gain rather than a broad paradigm shift.
The paper tackles the problem of inaccurate visual text rendering in text-to-image models by developing a customized text encoder, Glyph-ByT5, which improves text rendering accuracy from less than 20% to nearly 90% on a design image benchmark and enables high spelling accuracy for text paragraphs.
Visual text rendering poses a fundamental challenge for contemporary text-to-image generation models, with the core problem lying in text encoder deficiencies. To achieve accurate text rendering, we identify two crucial requirements for text encoders: character awareness and alignment with glyphs. Our solution involves crafting a series of customized text encoder, Glyph-ByT5, by fine-tuning the character-aware ByT5 encoder using a meticulously curated paired glyph-text dataset. We present an effective method for integrating Glyph-ByT5 with SDXL, resulting in the creation of the Glyph-SDXL model for design image generation. This significantly enhances text rendering accuracy, improving it from less than $20\%$ to nearly $90\%$ on our design image benchmark. Noteworthy is Glyph-SDXL's newfound ability for text paragraph rendering, achieving high spelling accuracy for tens to hundreds of characters with automated multi-line layouts. Finally, through fine-tuning Glyph-SDXL with a small set of high-quality, photorealistic images featuring visual text, we showcase a substantial improvement in scene text rendering capabilities in open-domain real images. These compelling outcomes aim to encourage further exploration in designing customized text encoders for diverse and challenging tasks.