Image tagging
The model labels what is in a picture: a scan sweeps it, yellow boxes draw around a bicycle, a tree, a dog and a kite with their confidence, the tags cascade in and a caption types.
Upload and analysisNo. 0792 variationsFree with an account
Playing on its own
Variation
- The idea
- The AI finds and labels what is in an image
- Autoplay
- A dotted scan sweeps the drawn park scene; four boxes draw on one after another with mono labels and confidence while their tags slide into the list; a caption types; the cursor hovers the dog so its tag lights, then hides the kite from its tag.
- When you click
- Hover a box to light its tag and dim the rest; hover or focus a tag to light its box; press a tag to hide or show its box; Scan again reruns the read. Keyboard: Tab, Enter or Space.
- Look
- boxes, draw on, mono labels type
- Variations
- Yellow on graphite, Moss
- Files
- index.html, style.css, script.js and prompt.md. No framework, no CDN, works offline.
The prompt and the files
Paste the prompt into Claude, ChatGPT, Lovable or any coding agent to rebuild it in your own product, or take the three files as they are.
Loading the files