Tutorial — Multi-modal AI

Detect objects with RF-DETR

RF-DETR is a permissively-licensed, NMS-free DETR family covering 90 COCO classes. The detection runtime also serves D-FINE for the smaller 80-class set.

Level: Beginner
Time: ~10 min
Prerequisites: Tenzro CLI installed, sample image
Stack: CLI · JSON-RPC

Load the detection model

The catalog has RF-DETR in six sizes (nano, small, medium, base, large, 2xl) — small is a good starting point.

curl -X POST https://rpc.tenzro.network -H 'content-type: application/json'   -d '{"jsonrpc":"2.0","id":1,"method":"tenzro_loadDetectionModel","params":["rfdetr-small"]}'

Run detection on an image

The CLI returns xyxy boxes in pixel coordinates with class labels and post-sigmoid scores.

tenzro detect image.jpg \
  --model rfdetr-small \
  --threshold 0.3

Switch to D-FINE for closed-class COCO

D-FINE returns post-sigmoid sorted boxes already in pixel space — fewer client-side steps.

curl -X POST https://rpc.tenzro.network -H 'content-type: application/json'   -d '{"jsonrpc":"2.0","id":1,"method":"tenzro_loadDetectionModel","params":["d-fine-s"]}'
tenzro detect image.jpg --model d-fine-s --threshold 0.4

Call from JSON-RPC

The RPC returns the same shape: an array of {bbox, label_id, score}.

curl -s https://rpc.tenzro.network -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tenzro_detect","params":{"model":"rfdetr-small","image_b64":"...","threshold":0.3}}'

Open the docs →Browse all tutorials

← All tutorials