# Wan 2.7 Pro Image-to-Image — Atlas Cloud API

> Edits and recomposes images with Wan 2.7 image pro using text instructions and multi-image references for higher quality outputs.

This is the machine-readable API reference for **Wan 2.7 Pro Image-to-Image** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `alibaba/wan-2.7-pro/image-edit`
- **Built by**: Alibaba
- **Modality**: Image
- **Model page**: https://www.atlascloud.ai/models/alibaba/wan-2.7-pro/image-edit
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.075 per image
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_image` with `model: "alibaba/wan-2.7-pro/image-edit"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate image alibaba/wan-2.7-pro/image-edit -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateImage` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `alibaba/wan-2.7-pro/image-edit`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  Model name.
  - Default: `"alibaba/wan-2.7-pro/image-edit"`
  - Options: "alibaba/wan-2.7-pro/image-edit"

- **`prompt`** (`string`, _required_):
  Text instruction used to edit the image. Maximum length is 5000 characters.

- **`images`** (`array[string]`, _required_):
  Input images, each provided as a URL or Base64 string. The first image is treated as the primary input; subsequent images serve as references.
  - Min items: 1
  - Max items: 9

- **`size`** (`string`, _optional_):
  Output image resolution.
  - Default: `"2K"`
  - Options: "1K", "2K"

- **`n`** (`integer`, _optional_):
  Number of images to generate.
  - Default: `1`
  - Min: 1
  - Max: 4

- **`thinking_mode`** (`boolean`, _optional_):
  Whether to enable thinking mode for higher-quality image generation.
  - Default: `true`

- **`seed`** (`integer`, _optional_):
  Random seed for image generation. Range: 0 to 2147483647. Use -1 for a random seed.
  - Default: `-1`
  - Min: -1
  - Max: 2147483647

- **`enable_sync_mode`** (`boolean`, _optional_):
  Whether to wait for generation to finish and return the final result directly in the response.
  - Default: `false`

- **`enable_base64_output`** (`boolean`, _optional_):
  Whether to return the generated image as a Base64 string instead of a URL.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "model": "alibaba/wan-2.7-pro/image-edit",
  "prompt": "",
  "images": [
    ""
  ]
}
```


**Full Example**:

```json
{
  "model": "alibaba/wan-2.7-pro/image-edit",
  "prompt": "",
  "images": [
    ""
  ],
  "size": "2K",
  "n": 1,
  "thinking_mode": true,
  "seed": -1,
  "enable_sync_mode": false,
  "enable_base64_output": false
}
```


### Output Schema

The API returns the following output format:


- **`code`** (`integer`, _optional_):

- **`message`** (`string`, _optional_):

- **`data`** (`string`, _optional_):



**Example Response**:

```json
{
  "code": 0,
  "message": "",
  "data": null
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/wan-2.7-pro/image-edit",
  "prompt": "",
  "images": [
    ""
  ],
  "size": "2K",
  "n": 1,
  "thinking_mode": true,
  "seed": -1,
  "enable_sync_mode": false,
  "enable_base64_output": false
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/alibaba/wan-2.7-pro/image-edit)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### Alibaba WAN 2.7 Pro Image Edit

**Alibaba WAN 2.7 Pro Image Edit** is the higher-fidelity image editing tier in the Wan 2.7 family. It is designed for instruction-guided edits and multi-image composition when output quality matters more than raw turnaround speed.

#### Why creators love it

* **Higher-quality edits:** Better fit for texture transfer, material changes, and polished visual refinement.
* **Multi-image composition:** Use one or more reference images alongside a text instruction.
* **Instruction-first workflow:** Good for scene restyling, object replacement, and composition-guided editing.
* **Practical control surface:** Supports flexible sizing, multiple variations, and consistent exploration with seed control.

#### Perfect for

* Premium campaign and commercial design edits.
* Product photography refinement and compositing.
* Creative teams building polished before/after variations from source assets.
* Professional creative teams that need stronger edit quality than the standard tier.

Recommended size guidance:

* Prefer `1K` or `2K` for edit scenarios.
* Even though the Pro family supports `4K` for text-only generation, image-involved scenarios should stay on the lower supported sizes.

#### How to Use

1. Provide the source image and add extra references when needed.
2. Write a direct instruction describing the transformation you want.
3. Choose the target `size`, usually `1K` or `2K`.
4. Review the edited outputs and keep the version with the best balance of fidelity and polish.

#### Pro tips

* Ask for one controlled edit at a time when you want stable, premium output.
* Add more references only when they serve a clear visual purpose.

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/alibaba/wan-2.7-pro/image-edit · Docs: https://www.atlascloud.ai/docs