All models

GPT Image 2

Text-to-image with GPT Image 2, optionally guided by a reference image

Generate Imagesv1.0.04 inputsIMAGE

a cozy reading nook beside a rain-streaked window, warm lamp light, watercolor style

GPT Image 2 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
Reference image
TEXT
TEXT
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.

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

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

const { outputs } = await runNode("gpt-image-2", {
  prompt: { value: "example" },
  image: { ref: "https://..." },
  size: { value: "1024x1024" },
  quality: { value: "medium" },
});

Schema

Every port this node publishes, with its type, its hint and the default it runs with. gpt-image-2 is the id you call.

Inputs

prompt*TEXT
imageIMAGE
Reference image
sizeTEXT
1024x1024 · 1536x1024 · 1024x1536
1024x1024
qualityTEXT
low · medium · high
medium

Outputs

imageIMAGE

Chain it with the rest of the catalog

Open the studio