Authors
- Yingxin Lai Xiamen University
- Yufei Liu Xiamen University
- Guoqing Yang Xiamen University
- Jiaxing Chai Xiamen University
- Zhiming Luo Xiamen University
- Shaozi Li Xiamen University
DOI:
https://doi.org/10.1609/aaai.v40i1.37019Abstract
Despite recent advancements in font generation, practitioners still grapple with a laborious trial-and-error workflow. To streamline this, we propose OneFont, an end-to-end framework that interprets user intents via free-form dialogue, seamlessly integrating both glyph synthesis and refinement modules. We introduce the Font with Thought (FwT) paradigm, reframing font design as a reasoning task where the model plans actions and articulates design rationales. OneFont’s core planner is trained via a two-stage regimen to master this paradigm. First, we instill reasoning abilities via Supervised Fine-Tuning (SFT) on a new, comprehensive benchmark of 1,500 font families we built. Second, we refine the model's policy with a novel reinforcement learning algorithm, Group Relative Policy Optimization (GRPO), guided by a hybrid reward that assesses visual fidelity, rationale coherence, and transformation correctness. Extensive experiments show OneFont significantly surpasses existing methods in design quality and stroke precision across diverse scripts, validated on our new benchmark. We will release our dataset, code, and models.
How to Cite
Lai, Y., Liu, Y., Yang, G., Chai, J., Luo, Z., & Li, S. (2026). OneFont: A Unified Agent for End-to-End Font Creation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 552–560. https://doi.org/10.1609/aaai.v40i1.37019
Issue
Section
AAAI Technical Track on Application Domains I