🤖 AI Summary
This study addresses the monotony and low user engagement in generative AI–driven public art installations by proposing “body prompting”—a novel paradigm that replaces textual prompts with human pose as the primary input modality to enable embodied human-AI co-creation. Methodologically, we integrate MediaPipe-based pose estimation, fine-tuned Stable Diffusion, real-time motion feature encoding, and multimodal prompt fusion to build a low-latency interactive generation system; we further design three embodied interaction strategies: replication, reconstruction, and improvisation. Deployed in a large-scale public event involving over 100 participants, the system yielded 79 user interviews indicating significant improvements in perceived fun and immersion. Feasibility and scalability are empirically validated across real-world cultural venues—including museums and art galleries—demonstrating robust applicability. This work contributes a reusable technical pipeline and a principled design framework for embodied generative AI interaction.
📝 Abstract
Image generation using generative artificial intelligence has become a popular activity. However, text-to-image generation - where images are produced from typed prompts - can be less engaging in public settings since the act of typing tends to limit interactive audience participation, thereby reducing its suitability for designing dynamic public installations. In this article, we explore body prompting as input modality for image generation in the context of installations at public event settings. Body prompting extends interaction with generative AI beyond textual inputs to reconnect the creative act of image generation with the physical act of creating artworks. We implement this concept in an interactive art installation, Artworks Reimagined, designed to transform existing artworks via body prompting. We deployed the installation at an event with hundreds of visitors in a public and private setting. Our semi-structured interviews with a sample of visitors (N = 79) show that body prompting was well-received and provides an engaging and fun experience to the installation's visitors. We present insights into participants' experience of body prompting and AI co-creation and identify three distinct strategies of embodied interaction focused on re-creating, reimagining, or casual interaction. We provide valuable recommendations for practitioners seeking to design interactive generative AI experiences in museums, galleries, and public event spaces.