CLIP-based Pre-Training of Chinese Font Contents and Styles
Shenglan Peng, Wei Feng, Donghong Yang · 2023
In this paper, we propose a CLIP-based extraction model of Chinese character content and font style. The model utilizes an embedding layer to encode Chinese characters and font style, a residual network to extract features from images, and a contrast loss to train the model. The results of experiments on a large-scale font dataset show that the features extracted by the CLIP model can effectively characterize different Chinese character contents and font styles, which also provides a good foundation for subsequent font generation tasks.