Interaction Modes and User Experience in Generative AI-Based New Media Art

This paper aims to explore how to utilize Generative Artificial Intelligence (GAI) to empower new media art creation that relies on different interactive modes, thereby bringing users new artistic experiences in the context of AI development. Presently, significant breakthroughs in artificial intelligence have had a profound impact on social development. Particularly, after the emergence of generative large models such as ChatGPT, Midjourney, and Stable Diffusion, GAI technology has more widely penetrated into various application scenarios, and it is redefining innovative pathways in artistic creation.Therefore, to better grasp the new media creation methods based on GAI, this paper primarily employs case analysis. Within the theoretical framework, we analyze the feasibility of combining new media art and GAI based on their developmental trajectories. Furthermore, we conduct an in-depth analysis of GAI new media artworks that rely on different interactive modes, exploring the specific applications of GAI in the field of new media art creation and the different experiential effects produced for users.Subsequently, the research results indicate that GAI can not only expand the creative dimensions of new media artists but also, by leveraging various interactive modes, provide users with more intelligent and multimodal artistic experiences. This aligns with the inevitable trend of artistic creation in the digital age. In conclusion, GAI is reshaping the creative paradigms of new media art. In this paper, we have provided new design strategies and creative methods for GAI-based new media art, clarifying the application value of GAI in new media art creation that relies on multiple interactive modes. From a design perspective, we offer new insights into how artificial intelligence can better enrich human artistic experiences, thereby providing new research perspectives and ideas for the development of art and technology.