Welcome to Closer,
a weekly newsletter where I take one of my photos, ask AI to describe it, then see what kind of image it can generate from its own description—an ongoing experiment in the capabilities of AI, and what that means for humans. This is edition #006.
A self portrait, because I'm curious to learn how AI would interpret me and what that interpretation of me could look like. Or less vain, a relatively complex image of a human taking a self portrait in a broken mirror. How much of those elements will AI get right?
You know the drill: human experience → photograph → AI description → synthetic image. Prompts are in the grey callout boxes, the AI description is cursive.
LLMs used
Midjourney V6.1 for image interpretation and image generation.
The input
The output
A photo of an attractive man taking his own picture in the mirror. He is wearing a black shirt and has short hair with shaved sides, sitting in a desk chair and holding a Sony A7R IV camera with a 24-70mm f/2.8 lens. The room looks clean and minimalistic, with white walls and natural lighting, shot from behind him looking into the full-frame mirror. --ar 128:85
This content is only available to subscribers
Subscribe now and have access to all our stories, enjoy exclusive content and stay up to date with constant updates.
Unlock contentAlready have an account? Sign In
