> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Wan2.5 Image

> Alibaba's Wan 2.5 image model with text-to-image and multi-reference editing of up to 3 images at about 1.7 megapixels.

![Wan2.5 Image](https://media.empiriolabs.ai/model-logos/wan.png)

[Alibaba Cloud](/providers/alibaba) · Image Generation

`POST /v1/images/generations`

Alibaba's Wan 2.5 image model with text-to-image and multi-reference editing of up to 3 images at about 1.7 megapixels.

## At a glance

| Field               | Value                                   |
| ------------------- | --------------------------------------- |
| Model id            | `wan2-5-image`                          |
| Model release date  | 2025-09-24                              |
| Input modalities    | Text, Image                             |
| Output modalities   | Image                                   |
| Context window      | -                                       |
| Weight precision    | -                                       |
| Region              | Singapore                               |
| Features            | image_generation, image_editing         |
| Native inference    | No                                      |
| New                 | No                                      |
| Supported endpoints | `POST /v1/images/generations`           |
| Alternate model ids | `alibaba/wan-2.5-image`, `wan2.5-image` |

## Pricing

| Charge   | Spec      | Rate    |
| -------- | --------- | ------- |
| Standard | per image | \$0.030 |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/images/generations \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "wan2-5-image", "prompt": "a misty forest at dawn", "size": "1024x1024"}'
```

## Parameters

| Parameter         | Type    | Required | Default | Description                                                                                                                |
| ----------------- | ------- | -------- | ------- | -------------------------------------------------------------------------------------------------------------------------- |
| `prompt`          | string  | yes      | -       | Text prompt (up to 2000 characters). With input images attached, becomes the editing instruction.                          |
| `aspect_ratio`    | enum    | no       | `"1:1"` | Output aspect ratio. · Allowed: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`                                          |
| `image`           | array   | no       | -       | Up to 3 input image URLs. Triggers editing mode.                                                                           |
| `num_images`      | number  | no       | `1`     | Number of images to generate. Each is billed separately. · Range: 1 – 4                                                    |
| `negative_prompt` | string  | no       | `""`    | What to avoid in the output.                                                                                               |
| `prompt_extend`   | boolean | no       | true    | Let the service rewrite the prompt for better results.                                                                     |
| `watermark`       | boolean | no       | false   | Add a provenance watermark to the output.                                                                                  |
| `seed`            | number  | no       | -       | Reproducibility seed. Leave empty for random. · Range: 0 – 2147483647                                                      |
| `response_format` | enum    | no       | `"url"` | Return signed image URLs by default, or include base64 image data when b64_json is requested. · Allowed: `url`, `b64_json` |

## Notes

Text-to-image renders about 1.7 megapixels at the chosen aspect ratio; attach 1 to 3 images for editing and fusion at about 1 megapixel. Prompts up to 2000 characters.

**Content safety**

* Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/wan2-5-image`.