Diffusion TV: Experiencing Diffusion Models through Tangible, Embodied Interaction
Researchers present Diffusion TV, a CRT-based installation where antenna manipulation lets audiences physically experience diffusion model denoising.
Diffusion TV is an interactive installation built around a modified CRT television where turning the antenna controls the clarity of AI-generated images and sounds, mirroring the denoising process of diffusion models. Three channels present AI-generated animals from the past, present, and future within a temporal and ecological narrative. The authors frame the work as an embodied, non-verbal alternative to explainable AI that highlights intermediate generative states rather than final outputs.
- Antenna manipulation on a modified CRT TV controls clarity of AI-generated images and sounds, enacting diffusion denoising.
- Three channels feature AI-generated extinct, endangered, and speculative species in an ecological narrative.
- Framed as an embodied, non-technical alternative to explainable AI emphasizing the generative process.
- Products
- Diffusion TV
From the original article
1 min read at arxiv.orgDiffusion TV is an interactive AI art installation that offers a tangible and embodied experience of diffusion models through a modified CRT TV. By physically manipulating the TV's antenna, audiences control the clarity of AI-generated images and sounds, metaphorically enacting the denoising process that underlies diffusion-based generation.
By Sihwa Park · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.