Platform
Checking your session…
← All models

QwenQwen 3.0 ProText → Image

Qwen-Image 3.0 Pro (GA) — flagship text-to-image and image editing with prompt-rewrite modes and thinking mode.

Image InputNegative Prompt2K

Install the SDK

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

npm install @picsart/ai-sdk

Authenticate

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

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.

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('qwen-image-3.0-pro', {
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  resolution: "2048x2048"
});

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

Parameters

9 parameters. Required ones must be supplied; the rest fall back to their defaults. The API takes these same names over HTTP.

ParameterTypeRequiredDefaultDetails
prompt
Prompt
textyes—max 800 chars
negativePrompt
Negative Prompt
textno—max 500 chars
resolutionenumno2048x20482048x2048, 2688x1536, 1536x2688, 2368x1728, 1728x2368
countenumno11, 2, 4, 6
enhancePromptbooleannotrue—
imageUrls
Source Images
file (image[])no——
seed
Seed
rangeno—0–2147483647 (step 1)
promptExtendModeenumnodirectdirect, agent
enableThinking
Deep Thinking
booleannotrue—

Output

generate() resolves once the job completes. One or more image URLs.

Result
{
  "items": [
    {
      "url": "https://cdn.picsart.com/…/result"
    }
  ],
  "model": "qwen-image-3.0-pro"
}