FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning
1South China University of Technology,
2SCUT-Zhuhai Institute of Modern Industrial Innovation,
3Alibaba Group
Abstract
Automatic font generation is an imitation task, which aims to create a font library that mimics the style of reference images while preserving the content from source images.
Although existing font generation methods have achieved satisfactory performance, they still struggle with complex characters and large style variations.
To address these issues, we propose FontDiffuser, a ...
Read more at yeungchenwa.github.io