Luma Flash 2

Luma · Video · Image → Video

Quick image-to-video with smooth, stylized motion — up to 4K.

Model ID: luma-ray-flash-2Workflow: luma-image-to-video-generation

Image InputStart/End FrameUp to 4K5/9 sec

Install the SDK

The SDK targets Node 20+ and ships with TypeScript types.

npm

npm install @picsart/ai-sdk

Authenticate

Create a client once with your API key — it's sent as a bearer token on every request.

TypeScript

import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY, // sent as: Authorization: Bearer <key>
  apiUrl: 'https://api.picsart.com',
});

Run the model

Call the model with its parameters. This example uses the required ones.

TypeScript

import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

const result = await ai.generate('luma-ray-flash-2', {
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  startFrame: "https://cdn.example.com/input.jpg"
});

console.log(result.url); // video URL

Parameters

6 parameters. Required ones must be supplied; the rest fall back to their defaults.

Parameter	Type	Required	Default	Details
`prompt` Prompt	`text`	yes	`—`	—
`aspectRatio`	`enum`	no	`16:9`	16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21
`resolution`	`enum`	no	`720p`	540p, 720p, 1080p, 4k
`duration`	`enum`	no	`5`	5, 9
`startFrame` Start Frame	`file (image)`	yes	`—`	—
`endFrame` End Frame	`file (image)`	no	`—`	—

Output

generate() resolves once the job completes. A video URL.

Result

{
  "url": "https://cdn.picsart.com/…/result",
  "results": [
    { "url": "https://cdn.picsart.com/…/result" }
  ],
  "model": "luma-ray-flash-2"
}