“How can we co-create with generative AI models in physical space?”

SPATIAL
CO-CREATION
WITH GEN AI

LSI is an experimental platform designed to explore the artistic potentials of Generative AI within immersive spatial installations. Visitors are invited to step into a fluid audiovisual environment that can be transformed through 3D video projection mapping.

In a collaborative process, participants assist open-source AI models in augmenting a physical environment. Algorithms generate artwork based on user input, while visitors modulate the resulting visual and auditory output via a touchscreen interface or through other sensor-based interactions.

EXPLORING
CAUSE
AND EFFECT

The initial proof-of-concept installation was evaluated as part of an exhibition at Designmonat Graz 2024. For this we created a custom graphical user interface built on symbolic language. At first glance, the UI appears strangely familiar, with its minimalist graphical elements and polished design. Yet, much like in the real world, visitors could not immediately discern how their collaborative actions influenced the simulated audiovisual environment around them.

CREDITS

CONCEPT, VIDEO PROJECTION MAPPING, SOUND
MO:YA (Werner Huber, Roland Mariacher)

GEN AI DEVELOPMENT
Roland Mariacher

TECHNOLOGY PARTNER
4Events GmbH