Generative AI-driven TouchDesigner Empowers Interactive Aesthetic Reconstruction and Creative Research of Digital Media Art
DOI:
https://doi.org/10.62177/jetp.v3i2.1429Keywords:
Generative AI, Digital Media Art, Interactive AestheticsAbstract
With the breakthrough development of generative AI technology, digital media art is undergoing a paradigm shift from "tool-assisted" to "intelligent symbiosis". This study takes TouchDesigner, which is powered by generative AI in real time, as the technical base, and focuses on its interactive aesthetic reconstruction mechanism and creative path innovation in digital media art creation. Through case evidence and technical analysis, this paper reveals how the technology combination reconstructs the creative logic, aesthetic experience and value dimension of digital media art through the three core capabilities of dynamic content generation, multimodal interactive feedback, and real-time visual computing. This paper proposes a three-dimensional reconstruction model of "intelligence-interaction-aesthetics", and verifies its innovative application in virtual production, interactive installation, immersive exhibition and other scenarios, providing theoretical support and practical paradigm for the intelligent transformation of digital media art.
Downloads
References
Li, X., Wang, H., & Chen, L. (2024). The Synergy of Generative AI and TouchDesigner: Redefining Real-Time Interactive Digital Media Art. Journal of Digital Art & Technology, 18(2), 45-62.
Wang, Y., & Zhang, Q. (2023). Transformer-Based Generative AI: Breaking the Boundaries of Traditional Digital Art Creation.International Journal of Media & Art Technology, 15(3), 78-95.
Chen, J., Liu, M., & Zhang, H. (2025). Cross-Platform Compatibility Optimization of TouchDesigner Based on WebAssembly Technology. IEEE Transactions on Visualization and Computer Graphics, 31(4), 1890-1902.
Sun, Y. (2026). The Interactive Shift and User Experience Reconstruction of Art Design in the Context of Digital Media. International Journal of Educational Research, 12(2), 92-105.
Brown, A., Davis, L., & Wilson, K. (2024). Latency Optimization Strategies for Generative AI in Real-Time Digital Art Applications. Computers & Graphics, 112, 104892.
Downloads
How to Cite
Issue
Section
License
Copyright (c) 2026 Wenju Gao

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.








