DETAILS:

“Fusion: Landscape and Beyond” — 聚变：山水与变革 (2022) is an interdisciplinary artwork, exploring the role of memory in imagination and creation through artificial intelligence (AI) and Chinese landscape painting. 

Inspired by the theory of Cultural Memory by Martin Kern which emphasizes the process of selectively retrieving and updating memory with the responses to the ever-changing present situations or requirements, we find that the current text-to-image AI algorithms can be thought of as analogous to this theory of Cultural Memory, in that they react to diverse human instructions with relatively fixed knowledge, i.e. checkpoints in pre-trained models. It shows different results based on both its formed dataset and the current inputs, producing more fantastic and unbridled images compared with the original ones in its dataset. In response to this analogy, we propose a novel concept called AI memory and link that to the Chinese landscape painting (Shan-Shui-Hua), which is traditionally created from the artist’s memory.

We created a video animation and series of still images with state-of-the-art AI technology, combining the symbolic elements of landscapes that span time and space to represent the past, present, and future through “AI memory.”

In addition, we will present a demo of an AI Chinese landscape poetry & painting generator, which represents our further research on applying AI in the study of visualizing the relationship of traditional Chinese painting and poetry.  

Contribution:

• Animation & Images Creation by Mingyong Cheng, Xuexi Dang, Xingwen Zhao
• AI Generative Tool Design & Development by Zetao Yu, Mingyong Cheng

Team:

• Mingyong Cheng: Artist & New Media Art Researcher, 2nd Year Ph.D. from Visual Arts; Advised by Professor Memo Akten and Pinar Yoldas
• Xuexi Dang: Chinese Art History Researcher, 2nd Year Ph.D. from Visual Arts; Advised by Professor Kuiyi Shen
• Xingwen Zhao: Chinese Poetry Researcher, M.A. in Chinese Studies from CUHK
• Zetao Yu: Professional Software Developer

Credits:

• This project used the code of open-source AI Art tools Stable Diffusion and Deforum. 
• Music: 鹤舞白沙 and 是我的脑海还是云的末端 by Amingliang from freesound.org under the Attribution 4.0 License
• Sound/Recording: Water Lap by snog, Rain Moderate by InspectorJ, Road Traffic Environment Ambix by KilianJosselinAlba from freesound.org under the Attribution 4.0 License

Special thanks to the IDEAS program and the UC San Diego Department of Visual Arts.