# Alibaba | Wan 2.7 | Image Edit

Alibaba Wan 2.7 Image Edit is the latest Wan-series image editing model by Alibaba, offering improved instruction comprehension and edit precision for a wide range of modifications including style changes, object edits, and scene alterations. Built on the Wan 2.7 architecture, it handles complex natural language edit instructions with greater semantic accuracy than earlier versions. Best suited for product photo editing, creative retouching, and high-volume commercial image transformation pipelines.

## API Information

- **Model Slug:** alibaba-wan-2-7-image-edit
- **Branded URL:** https://www.eachlabs.ai/alibaba/wan-2-7/alibaba-wan-2-7-image-edit
- **Provider:** Alibaba
- **Category:** Image to Image
- **Output Type:** array
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** 0.03/Per image pricing
- **Estimated Processing Time:** 10 seconds
- **Last Updated:** 2026-05-25
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/alibaba-wan-2-7-image-edit

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** 0.03/Per image pricing

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | 0.03/Per image pricing |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text instruction describing the desired editing operation. Supports Chinese and English. Max 5,000 characters. |
| img_url | string | Yes | - | - | URL of the primary input image to edit. Supported formats: JPEG, JPG, PNG, BMP, WEBP. Max 20 MB. |
| img_url_2 | string | No | - | - | URL of a second reference image (optional). |
| img_url_3 | string | No | - | - | URL of a third reference image (optional). |
| img_url_4 | string | No | - | - | URL of a fourth reference image (optional). |
| size | string | No | 2K | ["1K","2K"] | Output image resolution. 1K: ~1024px. 2K: ~2048px (default). Aspect ratio matches last input image. |
| n | integer | No | 1 | - | Number of images to generate. Range: 1-4. Each image is billed separately. |
| seed | integer | No | - | - | Seed for reproducibility. Same seed produces similar results. Random if omitted. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba-wan-2-7-image-edit",
  "input": {
    "prompt": "Turn image 1 into a oil painting.",
    "img_url": "https://storage.googleapis.com/magicpoint/inputs/alibaba-wan-2-7-image-edit-input.jpeg"
  }
}'
```

## 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 "X-API-Key: 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 `X-API-Key` |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

Alibaba | Wan 2.7 | Image Edit empowers users to transform existing images through precise text-guided instructions, solving the challenge of flexible and creative image manipulation without starting from scratch. Developed by Alibaba Tongyi Lab as part of the Wan 2.7 family, this image-to-image model leverages a unified architecture for generation and editing, enabling seamless adjustments like style transfers, element swaps, and multi-image fusions. Its primary differentiator is support for up to nine reference images in a single prompt, allowing complex edits such as blending multiple sources into cohesive outputs at resolutions up to 4K in the Pro variant. Available via the **Alibaba | Wan 2.7 | Image Edit API** on platforms like each::labs, it excels in realistic avatar customization and superior text rendering, making it ideal for designers and creators seeking professional-grade results.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `X-API-Key: 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.