Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation
Published in ACM MM Workshop 2025, 2025
We propose a Chinese calligraphy generation model based on Vision Mamba and TripleLabel mechanism for generating Chinese calligraphy of specified calligraphers, characters, and styles. We construct the Mobao dataset with over 1.9 million Chinese calligraphy images. The Moyun model achieves excellent performance in calligraphy structural fidelity and style matching.
Recommended citation: Kaiyuan Liu, Jiahao Mei, Hengyu Zhang, et al. "Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation." ACM MM Workshop, 2025.
Download Paper