Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| 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 |