GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows
This addresses a specific problem in text-to-image generation for applications requiring precise rendering, representing an incremental improvement over current methods.
The paper tackles the challenge of accurately generating complex text and mathematical formulas in text rendering by introducing GlyphBanana, a training-free agentic workflow that integrates auxiliary tools to inject glyph templates, achieving superior precision compared to existing baselines.
Despite recent advances in generative models driving significant progress in text rendering, accurately generating complex text and mathematical formulas remains a formidable challenge. This difficulty primarily stems from the limited instruction-following capabilities of current models when encountering out-of-distribution prompts. To address this, we introduce GlyphBanana, alongside a corresponding benchmark specifically designed for rendering complex characters and formulas. GlyphBanana employs an agentic workflow that integrates auxiliary tools to inject glyph templates into both the latent space and attention maps, facilitating the iterative refinement of generated images. Notably, our training-free approach can be seamlessly applied to various Text-to-Image (T2I) models, achieving superior precision compared to existing baselines. Extensive experiments demonstrate the effectiveness of our proposed workflow. Associated code is publicly available at https://github.com/yuriYanZeXuan/GlyphBanana.