# Qwen Image API via PiAPI

Base URL: https://api.piapi.ai
Auth: X-API-Key header (get your key at https://piapi.ai/workspace/key)

Documentation: {{docs:qwen-image}} Models

- Text-to-image: model "Qubico/qwen-image", task_type "txt2img" — $0.015 per image
- Image edit:    model "Qubico/qwen-image", task_type "image-edit" — $0.025 per image

## Text to Image

POST /api/v1/task
{
  "model": "Qubico/qwen-image",
  "task_type": "txt2img",
  "input": {
    "prompt": "A poster with the headline 'Harmony of Cultures' in English, Chinese, and Japanese",
    "negative_prompt": "",
    "seed": -1,
    "steps": 8,
    "width": 1024,
    "height": 1024,
    "flow_shift": 3
  }
}

Parameters: width/height up to 1024 (default 1024), steps up to 16 (default 8),
seed -1 = random, flow_shift 1–7 (default 3).

## Image Edit

POST /api/v1/task
{
  "model": "Qubico/qwen-image",
  "task_type": "image-edit",
  "input": {
    "image1": "https://example.com/source.jpg",
    "prompt": "Replace the English headline with 'Unity in Diversity', keep the layout",
    "negative_prompt": "",
    "seed": -1,
    "steps": 8,
    "flow_shift": 3
  }
}

Up to 3 source images via image1 / image2 / image3.

## Get Task Result

GET /api/v1/task/{task_id}

Status: "pending" → "processing" → "completed" or "failed"
Image URL: response.data.output.image_url (or output.image_urls[0])

## Quick Start

1. Get API key: https://piapi.ai/workspace/key
2. Top up: https://piapi.ai/workspace/billing
3. POST /api/v1/task
4. Poll GET /api/v1/task/{task_id} until "completed"
5. Get image from response.data.output