# Xoromancy

- Date: 2019-02
- Type: model
- Credit: Aman Tiwari & Gray Crawford
- Made with: BigGAN (DeepMind) + Leap Motion hand tracking
- Video: https://www.youtube.com/watch?v=3PoBWSgDe2o
- URL: https://aifilmhistory.org/entry/xoromancy

Two Carnegie Mellon students built the first real-time tool that let the human body steer a neural network's imagination. Xoromancy mapped a visitor's hand movements, tracked by a Leap Motion sensor, directly into the latent space of BigGAN, DeepMind's image generator. Gray Crawford announced it in February 2019: "like divination via movement."

The insight was that BigGAN's thousands of input variables were hopeless to navigate with sliders, but the human body is itself a high-dimensional control system. Tiwari built the pipeline in Unity and TensorFlow. Years before anyone typed a prompt, Xoromancy posed the question the field would inherit: not whether a model can generate an image, but how a human directs it.

Links:
- Announcement (X): https://x.com/graycrawford/status/1100935327374626818
- Xoromancy at INTERSECTIONS (YouTube): https://www.youtube.com/watch?v=3PoBWSgDe2o
- Frank-Ratchye STUDIO for Creative Inquiry — project page: https://studioforcreativeinquiry.org/project/xoromancy
- Gray Crawford — thesis & portfolio: https://graycrawford.com/thesis.html

---
Source: https://aifilmhistory.org/entry/xoromancy
Era: 2015-2021 · Before the Dawn
Last updated: 2026-09-12