Moyun可精准生成指定书家、字体和风格的汉字书法。
Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation
- 用Vision Mamba替代Diffusion中的Unet，提升生成效率
- 引入三标签控制机制，实现风格、书家、字形精确调控
- 在190万张书法图像上验证，能复现未写过字的风格
尽管汉字书法生成已实现风格迁移，但指定书家、字体和字形风格仍具挑战。为此，我们提出新模型Moyun，将扩散模型中的Unet替换为Vision Mamba，并引入三标签控制机制，实现可控书法生成。模型在包含超过190万张图像的大规模数据集Mobao上测试，结果表明，Moyun能有效控制生成过程，生成符合指定风格的书法作品。即使对书家未曾书写过的字，Moyun也能生成风格一致的书法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。