Summary
Making fonts look good in many languages is hard because each language needs carefully designed letters, colors, and spacing to match the original style. The paper presents LoGAN, a system that can take a few letters from a font or logo and create the full alphabet in different languages, including complex ones like Chinese and Korean. It combines several tools such as a model for creating letter images, a method to copy style and spacing, and an agent to coordinate these parts. Compared to other methods, LoGAN produces letters that look more faithful to the original style and fit well together. The authors tested it on fonts and logos across more than 27 languages to show its effectiveness.
font localizationglyph generationmultilingual font designspacing and kerningdiffusion modelstyle transfertexture expansionvisual language modelfew-shot learningcharacter set generation
Authors
Zhuoning Yuan, Ta-Ying Cheng, Benjamin Klein
Abstract
Localizing a font into new languages is a highly intricate task requiring precise design adaptation of glyphs, color/texture, and spacing/kerning, from source to target languages. Most existing methods focus on single glyph generation with limited capability in handling multilingual font rendering. In this work, we propose LoGAN, a VLM-based agentic framework for few-shot multilingual font localization, which takes in a small number of individual glyphs from a font or letters from a logo and uses them to generate complete character sets in other languages. LoGAN breaks down this task into multiple components: a glyph-level diffusion model, a style finetuning module, a spacing and kerning transfer algorithm, and a texture expansion model, with a VLM agent coordinator. LoGAN achieves broad language coverage for font localization with various styles, including Chinese/Korean/Japanese (CJK). We evaluate our approach on both font and real-world logo datasets spanning more than 27 languages and compare it against both specialized font generation and state-of-the-art image editing models with strong text rendering capabilities (e.g., FLUX, Nano-Banana). Our approach yields higher glyph fidelity while maintaining better style, texture, and kerning consistency according to both quantitative and qualitative evaluations.