All models

Grounded SAM (Text to Mask)

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

Edit & Analyze Imagev1.0.04 inputsIMAGE
Run it nowCall from code
Grounded SAM (Text to Mask) input
Grounded SAM (Text to Mask) output

Mask cut from the word “sneaker”

Try it right here

Fill the inputs the node publishes and run it on your own account. The same ports, defaults and types the studio uses.

Inputs

IMAGE
TEXT
Include (comma separated)
TEXT
Exclude (comma separated)
-50 – 50INT
Grow / shrink mask
Sign in to run

Running a model executes it on your account. Browsing the catalog stays free and needs no account.

Output

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

Call it from your code

The same node, called by id from any surface. Every tab pins this node and passes the ports below.

Read the 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 },
});

Schema

Every port this node publishes, with its type, its hint and the default it runs with. grounded-sam is the id you call.

Inputs

image*IMAGE
maskPrompt*TEXT
Include (comma separated)
negativeMaskPromptTEXT
Exclude (comma separated)
adjustmentINT
Grow / shrink mask
0

Outputs

maskIMAGE

Chain it with the rest of the catalog

Open the studio