Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Kaiyuan, Mei, Jiahao, Zhang, Hengyu, Zhang, Yihuai, Dong, Daoguo, He, Liang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917129622650880
author Liu, Kaiyuan
Mei, Jiahao
Zhang, Hengyu
Zhang, Yihuai
Dong, Daoguo
He, Liang
author_facet Liu, Kaiyuan
Mei, Jiahao
Zhang, Hengyu
Zhang, Yihuai
Dong, Daoguo
He, Liang
contents Although Chinese calligraphy generation has achieved style transfer, generating calligraphy by specifying the calligrapher, font, and character style remains challenging. To address this, we propose a new Chinese calligraphy generation model 'Moyun' , which replaces the Unet in the Diffusion model with Vision Mamba and introduces the TripleLabel control mechanism to achieve controllable calligraphy generation. The model was tested on our large-scale dataset 'Mobao' of over 1.9 million images, and the results demonstrate that 'Moyun' can effectively control the generation process and produce calligraphy in the specified style. Even for calligraphy the calligrapher has not written, 'Moyun' can generate calligraphy that matches the style of the calligrapher.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07618
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation
Liu, Kaiyuan
Mei, Jiahao
Zhang, Hengyu
Zhang, Yihuai
Dong, Daoguo
He, Liang
Computer Vision and Pattern Recognition
Artificial Intelligence
Although Chinese calligraphy generation has achieved style transfer, generating calligraphy by specifying the calligrapher, font, and character style remains challenging. To address this, we propose a new Chinese calligraphy generation model 'Moyun' , which replaces the Unet in the Diffusion model with Vision Mamba and introduces the TripleLabel control mechanism to achieve controllable calligraphy generation. The model was tested on our large-scale dataset 'Mobao' of over 1.9 million images, and the results demonstrate that 'Moyun' can effectively control the generation process and produce calligraphy in the specified style. Even for calligraphy the calligrapher has not written, 'Moyun' can generate calligraphy that matches the style of the calligrapher.
title Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2410.07618