Meme Me
ZKM, Kamuna, 2024
Meme Me is a playful yet critical installation that blurs the line between automated image recognition and internet culture. The work explores how artificial intelligence interprets visual content and repackages it into the internet’s most potent form of commentary: memes. Meme Me takes this mundane visual material and feeds it through a chain of AI perception and language generation, ultimately producing a meme that is both absurd and unsettlingly accurate.
How It Works
The process is deceptively simple:
- Visual Analysis — a background removal algorithm chooses 1 from many backgrounds that are chosen according to a theme.
- Screenshot Capture —the person presses a button and a 3 second countdown timer apprears on screen
- Visual Analysis — image is analyzed using a multimodal vision-language model. It looks for people, background, expressions and overall image context.
- Text Generation — the description fron the visual analysis is input into the text generation model (llama3) the model crafts short, meme-typical captions.
- Meme Creation — OpenCV overlays text on the original image in classic meme format.
Each step combines machine vision, natural language generation, and code to co‑create memes with both humor and unsettling accuracy. People can download or request to delete their images here.
