Imagev1.0.0

Grounded SAM (Text to Mask)

Turn a plain-text description of a subject into a cutout mask.

4 inputsIMAGE

Run it now Call from code

Mask cut from the word “sneaker”

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 grounded-sam 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("grounded-sam", {
  image: { ref: "https://..." },
  maskPrompt: { value: "example" },
  negativeMaskPrompt: { value: "" },
  adjustment: { value: 0 },
});

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

blitflow node grounded-sam \
  -i image=@https://... \
  -i maskPrompt="example" \
  -i negativeMaskPrompt="" \
  -i adjustment=0

{
  "name": "runs_node",
  "arguments": {
    "node": "grounded-sam",
    "inputs": {
      "image": {
        "ref": "https://..."
      },
      "maskPrompt": {
        "value": "example"
      },
      "negativeMaskPrompt": {
        "value": ""
      },
      "adjustment": {
        "value": 0
      }
    }
  }
}

curl https://studio.blitflow.com/api/v1/runs/node \
  -H "Authorization: Bearer $BLITFLOW_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"node":"grounded-sam","inputs":{"image":{"ref":"https://..."},"maskPrompt":{"value":"example"},"negativeMaskPrompt":{"value":""},"adjustment":{"value":0}}}'

Schema

Inputs

image*	IMAGE
maskPrompt*	TEXT	Include (comma separated)
negativeMaskPrompt	TEXT	Exclude (comma separated)
adjustment	INT	Grow / shrink mask	0

Outputs

mask