Skip to main content

​
Overview

Generate images from text descriptions using Flux, Nano Banana Pro, and other state-of-the-art AI models. This example walks you through the complete workflow from submitting a generation request to retrieving the final image.
Image generation is asynchronous. You’ll receive a job ID immediately, then poll for results until the image is ready.

​
Interactive Playground

Here’s a complete example in different languages: 
// npm install @krea-ai/sdk
import { Krea } from "@krea-ai/sdk";

const krea = new Krea({ apiKey: process.env.KREA_API_KEY });

const result = await krea.subscribe("image/bfl/flux-1-dev", {
  input: {
    prompt: "a serene mountain landscape at sunset",
    width: 1024,
    height: 576,
    steps: 28
  }
});

console.log(`Image ready: ${result.data?.urls[0]}`);
Replace with your API TokenTo replace the YOUR_API_TOKEN placeholder in the above examples, you’ll need to generate an API token in krea.ai/settings/api-tokens. Follow the instructions on the API Keys & Billing page if you need help.
To find all available models, see the Model APIs page.

​
Breakdown

Below, we’ll walk you through the complete workflow from submitting a generation request to retrieving the final image.

​
Step 1: Create an Image Generation Job

Make a POST request to /generate/image/bfl/flux-1-dev with your prompt and parameters. The API returns a job ID immediately—generation happens asynchronously. 
// npm install @krea-ai/sdk
import { Krea } from "@krea-ai/sdk";

const krea = new Krea({ apiKey: process.env.KREA_API_KEY });

const job = await krea.image("bfl/flux-1-dev", {
  prompt: "a serene mountain landscape at sunset",
  width: 1024,
  height: 576,
  steps: 28
});

console.log(`Job ID: ${job.job_id}`);
Example Response 
{
  "job_id": "550e8400-e29b-41d4-a716-446655440000",
  "status": "queued",
  "created_at": "2025-01-15T10:30:00.000Z"
}

​
Step 2: Poll for Results

Poll /jobs/{job_id} every 2 seconds until the job completes. The Krea API provides intermediate generation outputs for some models. 
// npm install @krea-ai/sdk
import { Krea } from "@krea-ai/sdk";

const krea = new Krea({ apiKey: process.env.KREA_API_KEY });

async function waitForJob(jobId) {
  const completed = await krea.jobs.wait(jobId, { intervalMs: 2000 });
  return completed.result.urls[0];
}

const imageUrl = await waitForJob(job.job_id);
console.log(`Image ready: ${imageUrl}`);
Webhooks available!Set up webhooks to receive notifications when jobs complete. See the Webhooks guide to get started.
For a list of detailed parameters for all models, see the Model APIs page.
Example Completed Response 
{
  "job_id": "550e8400-e29b-41d4-a716-446655440000",
  "status": "completed",
  "created_at": "2025-01-15T10:30:00.000Z",
  "completed_at": "2025-01-15T10:30:25.000Z",
  "result": {
    "urls": [
      "https://krea.ai/generations/your-image.png"
    ]
  }
}
To learn about all possible job statuses and the complete job lifecycle, check out the Job Lifecycle page.