Image & Model

Model Face

Classification
Mixed-media installation; thermal receipt prints of machine-learning dataset portraits, custom software, CRT monitor
Dimensions
Receipt panel approx. 70.8 × 59 inches; overall dimensions variable
Ref.
RC-14
Date
2026

From a distance, thousands of small portraits form a single, unfamiliar face. Up close, it breaks apart into individual receipts, each printed with a different person’s photograph. The large face is “This Man,” from a viral 2009 internet hoax in which strangers around the world supposedly dreamed of the same person.

Record

I became interested in the story after noticing how often AI image generators produced similar-looking faces, even from different prompts. I used Python to download portraits from an open machine-learning dataset on GitHub, designed the receipts, and printed each one on a thermal printer I modified with a Bluetooth module.

I wanted viewers to see the image at two distances: first as one face, then as many individuals. The work asks whether training future AI models on generated images could slowly narrow the range of faces they produce, and how easily thousands of identities can disappear into one repeated image.

A wall of receipt prints forming one large face, with a CRT monitor and printer in front
Fig. 1 Model Face, installation view. Ryan Chen, 2026.