metaai·lightalo unofficial · independent
The Lab / Segment Anything

Click an object. The real SAM masks it.

This is not a video or an API call. The picture's embedding was computed by Meta's Segment Anything ViT-B encoder on a Raspberry Pi, and the actual SAM mask decoder — 4 million of the model's real weights, quantized to 8-bit — is running in your browser right now via WebAssembly. model runs locally

Loading the model…

Click adds a point on the thing you want · shift-click marks what you don't want (refines the mask) · move the mouse to preview before clicking.

1.1B

masks taught it

SAM was trained on SA-1B: 11 million images, 1.1 billion masks — ~400× more masks than any prior dataset. That's why it segments objects it has never seen.

2

halves of one model

A heavy image encoder (ran once per photo, on a Raspberry Pi 5, offline) and a featherweight prompt decoder — the part answering your clicks in tens of milliseconds, locally.

~8MB

in your tab

The decoder you just downloaded is the genuine sam_vit_b decoder, exported to ONNX and 8-bit quantized — the exact architecture from Meta's own browser demo.

Apache 2.0

fully open

Code and weights are open source. Read the paper, browse the repo, or meet the whole family on the Universe map.