All models

Muse Image

Meta's image generation and editing model, blending a reference into the prompt

Generate Imagesv1.0.02 inputsIMAGE
Run it nowCall from code

an oil painting of a harbour at dusk, thick impasto brushwork, lantern reflections

Muse Image output

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

TEXT
IMAGE
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("muse-image", {
  prompt: { value: "example" },
  reference: { ref: "https://..." },
});

Schema

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

Inputs

prompt*TEXT
referenceIMAGE

Outputs

imageIMAGE

Chain it with the rest of the catalog

Open the studio