Imagev1.0.0

Grounding DINO (Detect)

Locate objects named in plain text, as boxes plus an annotated image.

4 inputsSTRUCTUREDIMAGE

Run it now Call from code

Objects located from the words “subject, background”

Output

Fill in the inputs and run the node to see its output here.

Run it from your code

The same node, called by id from any surface. Every tab pins grounding-dino and passes the ports below. Full guide.

import { BlitClient } from "@blitflow/sdk";

const { runNode } = new BlitClient({ apiKey: process.env.BLITFLOW_TOKEN });

const { outputs } = await runNode("grounding-dino", {
  image: { ref: "https://..." },
  query: { value: "example" },
  boxThreshold: { value: 0.25 },
  textThreshold: { value: 0.25 },
});

# Install once, then sign in
npm install -g blitflow
blitflow login

blitflow node grounding-dino \
  -i image=@https://... \
  -i query="example" \
  -i boxThreshold=0.25 \
  -i textThreshold=0.25

{
  "name": "runs_node",
  "arguments": {
    "node": "grounding-dino",
    "inputs": {
      "image": {
        "ref": "https://..."
      },
      "query": {
        "value": "example"
      },
      "boxThreshold": {
        "value": 0.25
      },
      "textThreshold": {
        "value": 0.25
      }
    }
  }
}

curl https://studio.blitflow.com/api/v1/runs/node \
  -H "Authorization: Bearer $BLITFLOW_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"node":"grounding-dino","inputs":{"image":{"ref":"https://..."},"query":{"value":"example"},"boxThreshold":{"value":0.25},"textThreshold":{"value":0.25}}}'

Schema

Inputs

image*	IMAGE
query*	TEXT	Objects (comma separated)
boxThreshold	FLOAT		0.25
textThreshold	FLOAT		0.25

Outputs