Thomas
A camera whose film is language.
Point it at the world. A vision model running on your iPhone says what it sees, then a second model draws the scene again from those words alone, having never seen your photograph.
Three frames, one press
Reality, machine perception, machine re-imagining. The photograph the lens took, the words a vision model wrote about it, and a drawing made from nothing but those words.
On-device and private
Both models run on your iPhone. Your photographs are processed by local models. No accounts, no servers, no tracking.
The eye
Choose which machine looks. Apple Intelligence is built in and needs no download. Qwen is downloadable and sees differently. Its system prompt and its temperature are yours to read and to change, and they are called a system prompt and a temperature.
The hand
A diffusion model draws the scene again, and it never sees your photograph. It works from the eye's words alone. That is the whole reason the third frame is worth looking at.
It says what it sees
No hedging, no confidence scores, no apology chrome. The machine states its perception plainly, and your photograph is sitting right there beside it. The juxtaposition is the disclaimer.
How the frames meet
Words laid on the world, a diptych, a triptych of all three, or the words alone. Every frame stamped with the place and the time, the way cameras always have.
The gap is the art.