Loading Now

Summary of Moyun: a Diffusion-based Model For Style-specific Chinese Calligraphy Generation, by Kaiyuan Liu et al.


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

by Kaiyuan Liu, Jiahao Mei, Hengyu Zhang, Yihuai Zhang, Xingjiao Wu, Daoguo Dong, Liang He

First submitted to arxiv on: 10 Oct 2024

Categories

  • Main: Computer Vision and Pattern Recognition (cs.CV)
  • Secondary: Artificial Intelligence (cs.AI)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
In this paper, researchers tackle a challenging task: generating Chinese calligraphy by specifying the calligrapher, font, and character style. They propose a new model called 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 a large-scale dataset of over 1.9 million images, demonstrating its ability to generate calligraphy in the specified style.
Low GrooveSquid.com (original content) Low Difficulty Summary
The Moyun model can create Chinese calligraphy by specifying the calligrapher, font, and character style. This is important because current methods only achieve style transfer but not controllable generation. The researchers used a large dataset of over 1.9 million images to test their model.

Keywords

» Artificial intelligence  » Diffusion model  » Style transfer  » Unet