Naturality: A Natural Reflection of Chinese Calligraphy

Bingyuan Wang, Kang Zhang, Zeyu Wang
The Hong Kong University of Science and Technology (Guangzhou)


We present a machine learning-based interactive video installation powered by CLIP and diffusion models and inspired by the concept of naturality in traditional Chinese calligraphy. The artwork explores contemporary interpretations of this traditional concept through practical methods in Artificial Intelligence Generated Content (AIGC). Technically, the algorithms are based on state-of-the-art perceptual and generative models, incorporating multi-dimensional controls over text-to-image and image-to-image translation; conceptually, this real-time art installation extends the discussion brought by Xu Bing’s pieces Book from the Sky and Square Word Calligraphy. The project explores the possibility of AIGC in bridging human creativity and natural randomness, as well as a shifting creative paradigm enhanced by AI knowledge, perception, and association.

BibTeX copied to clipboard