Diffusion 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. Using the tuning knob, participants switch between three channels featuring AI-generated animals from the Past (extinct species), Present (endangered species), and Future (speculative creatures), situating the interaction within a temporal and ecological narrative. Through continuous audiovisual feedback and physical interaction, Diffusion TV foregrounds the generative process over final outputs, allowing audiences to explore intermediate states as experiential material. Rather than providing explicit technical explanation, the work presents an alternative, embodied mode of explainable AI that invites exploratory engagement with and reflection on generative technologies.
Figures & tables
Figure 1. Content display sequence with antenna interaction: (a) the noisiest image of an animal, (b) an intermediate denoising state as the antenna rotates, (c) the final denoised image with additional information, and (d) when no rotation input is detected, the noisiest image of the next animal appears after a few seconds. Images showing how content updates in response to antenna rotation.
Figure 2. Schematic diagram of Diffusion TV Schematic diagram illustrating components of Diffusion TV, their connections, and data flows, including a Python content generator in Google Colab, a shared Google Drive storage, a Raspberry Pi 5 running a Processing client program and Python sensor module, an HDMI-RF modulator, and a CRT TV with rotary and magnetic encoders.
Figure 3. Diffusion TV installation Image of the Diffusion TV installation where a person is interacting with the work holding the antenna of a CRT TV placed on a pedestal.