Detect objects in any image. Runs entirely in your browser.
This tool uses the DETR (Detection Transformer) model with a ResNet-50 backbone, running entirely in your browser via Transformers.js. The model downloads once (approx 40MB) and is then cached. Your image is never uploaded to any server.
The model is trained on the COCO dataset and can detect 80 common object categories like person, car, dog, cat, etc.
No. All processing happens in your browser.