ComfyUI is an open source, node-based program that allows users to generate images from a series of text prompts. It uses free diffusion models such as Stable Diffusion as the base model for its image capabilities combined with other tools such as ControlNet and LCM Low-rank adaptation with each tool being represented by a node in the program. https://github.com/comfyanonymous/ComfyUI
Synthetic Spirits – Kinetic sculptures reveal a hidden world
Kinetic installation exploring tsukumogam — everyday objects that acquire spirits. A sake bottle and straw sandal glide past screens as generative AI reveals yokai spirits, contrasting folklore with today's throwaway culture.
Datalake:Groundtruth – Algorithmic hyperrealism
Datalake:Groundtruth is a triptych that takes the viewer into a series of ever-changing landscapes, marked by catastrophic events such as floods, landslides, fires, explosions, and the continuous destruction and construction of buildings and artif...
Habsburg AI Portrait Studies
Habsburg AI Portrait Studies is a series of cloth-printed generative portrait images produced using a bespoke diffusion model recursively retrained on its own output. This autophagous training causes the model to collapse on itself, constricting t...
Atmospheric Synthesis
“Cloudscape,” is an immersive installation that explores the intersection of physical and digital environments. By combining generative AI visuals with fog machines, we created a cloud-like atmosphere that blurs the boundaries between reality and ...
Transferscope – Synthesized Reality
Transferscope is a working prototype that merges a a single-button handheld aparatus with artificial intelligence, allowing the user to view and synthesize the physical world around them.
Activity Log
Join our Community to View/Add Comments.