# Alibaba | Qwen Image 2.0 | Image Edit

Qwen Image 2.0 Edit transforms images with style transfer, object insertion, text editing, and multi-image compositing for fast iteration on eachlabs.

## API Information

- **Model Slug:** alibaba-qwen-image-2-0-image-edit
- **Branded URL:** https://www.eachlabs.ai/alibaba/qwen-image-2-0/alibaba-qwen-image-2-0-image-edit
- **Provider:** Alibaba
- **Category:** Image to Image
- **Output Type:** array
- **Status:** active
- **Base Cost:** $0.035 per image
- **Estimated Processing Time:** 5 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/alibaba-qwen-image-2-0-image-edit

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.035 per image
- **Pricing Details:** default: $0.035

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Editing instruction. Supports Chinese and English. Max 800 characters. |
| image_urls | array | Yes | - | - | 1 to 3 input images. Formats: JPG, JPEG, PNG, BMP, TIFF, WEBP, GIF. Resolution 384-3072 px, max 10 MB. The output aspect ratio is determined by the last image. |
| negative_prompt | string | No | - | - | Describes content to exclude from the edit. Max 500 characters. |
| size | string | No | 1024*1024 | 1024*1024, 1536*1536, 1280*720, 1920*1080, 720*1280, 1080*1920, 1280*960, 1440*1080, 960*1280, 1080*1440, 1152*768, 1536*1024, 768*1152, 1024*1536, 1344*576, 2048*872 | Output resolution as width*height. 1:1 (1024*1024, 1536*1536), 16:9 (1280*720, 1920*1080), 9:16 (720*1280, 1080*1920), 4:3 (1280*960, 1440*1080), 3:4 (960*1280, 1080*1440), 3:2 (1152*768, 1536*1024), 2:3 (768*1152, 1024*1536), 21:9 (1344*576, 2048*872). |
| n | integer | No | 1 | 1–4 | Number of images to generate. 1-4. |
| seed | integer | No | - | 0–2147483647 | Random seed for reproducible generation. Range: 0-2147483647. |
| prompt_extend | boolean | No | true | - | Enable LLM-based prompt rewriting for better editing quality. Default: true. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba-qwen-image-2-0-image-edit",
  "input": {
    "image_urls": [
      "https://cdn-us.eachlabs.ai/defaults/ee35fcd4d19a447f8847f62e8999f8c2.png"
    ],
    "prompt": "Keep the room structure, walls, windows and layout exactly the same. Only replace the furniture with elegant luxury pieces. Add a sleek velvet sofa in deep emerald green, gold accent side tables, a marble coffee table, and sophisticated armchairs. Keep everything else unchanged."
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "array",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**Alibaba | Qwen Image 2.0 | Image Edit Overview**

Alibaba | Qwen Image 2.0 | Image Edit is a powerful image-to-image AI model from Alibaba's Qwen family, designed to transform input images based on text prompts for precise editing and generation tasks. It solves the challenge of detailed image manipulation, allowing users to modify specific elements like objects, styles, or compositions without starting from scratch. As part of the advanced Qwen Image 2.0 series, this model stands out with its native multimodal understanding, combining vision and language processing for superior instruction-following in edits compared to traditional tools.

Developed by Alibaba Cloud, Alibaba | Qwen Image 2.0 | Image Edit supports complex edits such as inpainting, outpainting, and style transfer, making it ideal for creative professionals seeking high-fidelity results. Available via the **Alibaba | Qwen Image 2.0 | Image Edit API** on platforms like each::labs, it enables seamless integration into workflows for rapid prototyping and content creation. Whether enhancing photos or generating variations, this model delivers consistent, high-quality outputs.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.