Six projects, laid out in space. Scroll to fly through them in order, or jump in from the index: a museum install with talking veterans, digital humans, and the AI R&D behind them.
Exhibits for the Canadian Warplane Heritage Museum: an immersive dome, interactive portrait portals and a cinema. I built the voice pipeline that gave each veteran back their younger voice from about an hour of audio.
Concept renders for immersive rooms, made with LoRAs trained on decades of my own installation mockups.
Testing open-source image-to-3D models (TRELLIS, SAM 3D, Hunyuan3D) on a single RTX 4090, then taking the results into Blender and Unreal.
Toys that never existed: 1970s-style action figures in boxes and blister packs, iterated with image-to-image workflows in ComfyUI.
An R&D series of impossible halls: one-point-perspective corridors lined with figures, iterated with custom LoRAs in ComfyUI.
A running log of experiments at the edge of local AI video and sound. Mostly failures. Updated often.
Works in progress, pipeline experiments, things that broke interestingly. The mess is part of it.
I've spent 25 years making interactive installations and mixed reality. I work in the gap between creative and technical teams: I prototype in Unreal, run it through generative AI workflows I build myself, and art-direct what comes out. Then I do the parts around it: sound, graphics, lighting, UX, and showing up on site for the install.
For Making Freedom Fly that meant rebuilding WWII veterans' younger voices from an hour of audio each, then designing the rooms visitors hear them in.
I'm not chasing hyperrealism. I want characters and worlds that couldn't have come from anyone else.
Available for studio roles, creative technology partnerships, and projects that need someone who designs the stuff and the thing. Based in Vancouver, BC. Open to remote.