FontAdapter: Instant Font Adaptation in Visual Text Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913881372229632 |
|---|---|
| author | Koo, Myungkyu Kim, Subin Kwak, Sangkyung Nam, Jaehyun Kim, Seojin Shin, Jinwoo |
| author_facet | Koo, Myungkyu Kim, Subin Kwak, Sangkyung Nam, Jaehyun Kim, Seojin Shin, Jinwoo |
| contents | Text-to-image diffusion models have significantly improved the seamless integration of visual text into diverse image contexts. Recent approaches further improve control over font styles through fine-tuning with predefined font dictionaries. However, adapting unseen fonts outside the preset is computationally expensive, often requiring tens of minutes, making real-time customization impractical. In this paper, we present FontAdapter, a framework that enables visual text generation in unseen fonts within seconds, conditioned on a reference glyph image. To this end, we find that direct training on font datasets fails to capture nuanced font attributes, limiting generalization to new glyphs. To overcome this, we propose a two-stage curriculum learning approach: FontAdapter first learns to extract font attributes from isolated glyphs and then integrates these styles into diverse natural backgrounds. To support this two-stage training scheme, we construct synthetic datasets tailored to each stage, leveraging large-scale online fonts effectively. Experiments demonstrate that FontAdapter enables high-quality, robust font customization across unseen fonts without additional fine-tuning during inference. Furthermore, it supports visual text editing, font style blending, and cross-lingual font transfer, positioning FontAdapter as a versatile framework for font customization tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05843 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FontAdapter: Instant Font Adaptation in Visual Text Generation Koo, Myungkyu Kim, Subin Kwak, Sangkyung Nam, Jaehyun Kim, Seojin Shin, Jinwoo Computer Vision and Pattern Recognition Text-to-image diffusion models have significantly improved the seamless integration of visual text into diverse image contexts. Recent approaches further improve control over font styles through fine-tuning with predefined font dictionaries. However, adapting unseen fonts outside the preset is computationally expensive, often requiring tens of minutes, making real-time customization impractical. In this paper, we present FontAdapter, a framework that enables visual text generation in unseen fonts within seconds, conditioned on a reference glyph image. To this end, we find that direct training on font datasets fails to capture nuanced font attributes, limiting generalization to new glyphs. To overcome this, we propose a two-stage curriculum learning approach: FontAdapter first learns to extract font attributes from isolated glyphs and then integrates these styles into diverse natural backgrounds. To support this two-stage training scheme, we construct synthetic datasets tailored to each stage, leveraging large-scale online fonts effectively. Experiments demonstrate that FontAdapter enables high-quality, robust font customization across unseen fonts without additional fine-tuning during inference. Furthermore, it supports visual text editing, font style blending, and cross-lingual font transfer, positioning FontAdapter as a versatile framework for font customization tasks. |
| title | FontAdapter: Instant Font Adaptation in Visual Text Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.05843 |