metaai·lightalo unofficial · independent
The Lab / Your photo

Your photo, through DINOv2's eyes

The rainbow slider used our photos. This one uses yours: Meta's DINOv2 ViT-S/14 — the actual network, 8-bit quantized to 23 MB — runs inside this tab on WebAssembly, and the famous PCA "rainbow" is computed in plain JavaScript. 🔒 nothing leaves your device

Drop a photo here, or
First use downloads the 23 MB model once (cached after). Photos are centre-cropped to a square and processed locally; we never upload them anywhere.
your photowhat DINOv2 sees
Working…

Wipe drags the divider · blend overlays the features · find similar: hover or touch a spot and every patch the model considers alike lights up.

What just happened

Your photo was centre-cropped to a 518×518 square and cut into 1,369 patches of 14×14 pixels. DINOv2 turned each patch into a 384-number vector. We projected those vectors onto their 3 main directions (PCA) and painted them as red, green and blue. Similar colours = similar features.

Why the black background?

The first principal component almost always separates "the thing" from "the background", so — like the DINOv2 paper — we keep only the foreground side and colour it with the next three components.

Go deeper

DINOv2 paper · code & weights (Apache 2.0) · DINOv2 on the map · runtime: onnxruntime-web (MIT).