Few-shot Calligraphy Style Learning

TL;DR

This paper presents Presidifussion, a diffusion-based model that learns and replicates calligraphy styles, especially President Xu's, using minimal data and innovative conditioning techniques, advancing digital preservation of calligraphic art.

Contribution

Introduces Presidifussion, a novel diffusion model with font and stroke conditioning, achieving high-quality calligraphy style replication with limited data and computational resources.

Findings

Comparable performance to traditional methods with less data

Effective style replication of President Xu's calligraphy

Reduced computational requirements for style learning

Abstract

We introduced "Presidifussion," a novel approach to learning and replicating the unique style of calligraphy of President Xu, using a pretrained diffusion model adapted through a two-stage training process. Initially, our model is pretrained on a diverse dataset containing works from various calligraphers. This is followed by fine-tuning on a smaller, specialized dataset of President Xu's calligraphy, comprising just under 200 images. Our method introduces innovative techniques of font image conditioning and stroke information conditioning, enabling the model to capture the intricate structural elements of Chinese characters. The effectiveness of our approach is demonstrated through a comparison with traditional methods like zi2zi and CalliGAN, with our model achieving comparable performance using significantly smaller datasets and reduced computational resources. This work not only presents a breakthrough in the digital preservation of calligraphic art but also sets a new standard for data-efficient generative modeling in the domain of cultural heritage digitization.