# Wan 3.0 Reference to Video

> AI model for generating video content

## Overview

- **Model ID**: `wan3.0-r2v`
- **Category**: video
- **Provider**: alibaba_cloud
- **Source Type**: Closed Source Model
- **Status**: model_ready
- **Screenshot**: `https://assets.modelslab.ai/generations/7a0bfab2-a882-4006-8373-189b4bf04a8b.webp`

## API Information

This model can be used via our HTTP API. See the API documentation and usage examples below.

### Endpoint

- **URL**: `https://modelslab.com/api/v7/video-fusion/image-to-video`
- **Method**: POST

### Parameters

- **`init_image`** (required): Add the image to convert it to video using prompt
  - Type: array

- **`init_audio`** (required): Add your reference audio
  - Type: array

- **`init_video`** (required): Add your reference video
  - Type: array

- **`model_id`** (optional): Model_id for selecting the model from mutiple models
  - Type: text

- **`prompt`** (required): Enter a prompt to define the actions you want your image to perform.
  - Type: textarea

- **`duration`** (required): 
  - Type: number (range: 4-30)

- **`resolution`** (required): Resolution is the amount of detail  video display can show.
  - Type: select (options: 720P, 1080P, 480P)

- **`aspect_ratio`** (required): Select the Aspect ratio
  - Type: select (options: 16:9, 9:16, 1:1, 4:3, 3:4)

## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://modelslab.com/api/v7/video-fusion/image-to-video \
  --header "Content-Type: application/json" \
  --data '{
    "key": "YOUR_API_KEY",
    "model_id": "wan3.0-r2v",
    "prompt": "At a Qin-dynasty battlefield site on a loess plateau, the setting sun is blood-red, a broken war chariot half-buried in yellow earth, and wind whips up sand. The shot racks focus from the chariot wreckage to a woman in red holding a pipa on a distant slope; she begins to play "Ambush from Ten Sides," the steel strings producing sharp, piercing tones like clashing weapons, her right-hand rolling fingers building a dense wall of sound like ten thousand galloping horses, and sweeps like blade slashes. From the first note the camera charges forward, its speed increasing in sync with the rolling-finger density; her left hand pushes and pulls the high positions so the pitch rises sharply like a warhorse's neigh, while the wind is swallowed by the pipa as battlefield cries overwhelm everything. The final sweep explodes from lowest to highest string, then absolute silence for two seconds, only the wind remains.",
    "duration": "5",
    "resolution": "480P",
    "aspect_ratio": "16:9"
  }'
```

### Python

```python
import requests

response = requests.post(
    "https://modelslab.com/api/v7/video-fusion/image-to-video",
    headers={
        "Content-Type": "application/json"
    },
    json={
        "key": "YOUR_API_KEY",
        "model_id": "wan3.0-r2v",
        "prompt": "At a Qin-dynasty battlefield site on a loess plateau, the setting sun is blood-red, a broken war chariot half-buried in yellow earth, and wind whips up sand. The shot racks focus from the chariot wreckage to a woman in red holding a pipa on a distant slope; she begins to play "Ambush from Ten Sides," the steel strings producing sharp, piercing tones like clashing weapons, her right-hand rolling fingers building a dense wall of sound like ten thousand galloping horses, and sweeps like blade slashes. From the first note the camera charges forward, its speed increasing in sync with the rolling-finger density; her left hand pushes and pulls the high positions so the pitch rises sharply like a warhorse's neigh, while the wind is swallowed by the pipa as battlefield cries overwhelm everything. The final sweep explodes from lowest to highest string, then absolute silence for two seconds, only the wind remains.",
        "duration": "5",
        "resolution": "480P",
        "aspect_ratio": "16:9"
    }
)

print(response.json())
```

### JavaScript

```javascript
fetch("https://modelslab.com/api/v7/video-fusion/image-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "key": "YOUR_API_KEY",
    "model_id": "wan3.0-r2v",
    "prompt": "At a Qin-dynasty battlefield site on a loess plateau, the setting sun is blood-red, a broken war chariot half-buried in yellow earth, and wind whips up sand. The shot racks focus from the chariot wreckage to a woman in red holding a pipa on a distant slope; she begins to play "Ambush from Ten Sides," the steel strings producing sharp, piercing tones like clashing weapons, her right-hand rolling fingers building a dense wall of sound like ten thousand galloping horses, and sweeps like blade slashes. From the first note the camera charges forward, its speed increasing in sync with the rolling-finger density; her left hand pushes and pulls the high positions so the pitch rises sharply like a warhorse's neigh, while the wind is swallowed by the pipa as battlefield cries overwhelm everything. The final sweep explodes from lowest to highest string, then absolute silence for two seconds, only the wind remains.",
    "duration": "5",
    "resolution": "480P",
    "aspect_ratio": "16:9"
  })
})
.then(response => response.json())
.then(data => console.log(data));
```

## Integration Options

### CLI

Install: `curl -fsSL https://modelslab.sh/install.sh | sh` or `brew install modelslab/tap/modelslab`

```bash
modelslab auth login                                    # Authenticate
modelslab models search "wan3.0-r2v"                       # Find this model
modelslab models detail --id wan3.0-r2v                    # Get model details
modelslab generate image --prompt "..." --model wan3.0-r2v  # Generate with model
modelslab config set generation.default_model wan3.0-r2v   # Set as default
```

- Website: https://modelslab.sh
- GitHub: https://github.com/ModelsLab/modelslab-cli

### MCP Servers (Model Context Protocol)

For Claude Code, Cursor, VS Code, Windsurf, and any MCP-compatible agent.

- Generation: `https://modelslab.com/mcp/v7` (API key auth, 23 tools)
- Agent Control Plane: `https://modelslab.com/mcp/agents` (Bearer token auth, 10 tools)

Claude Code config (`~/.claude/settings.json`):

```json
{
  "mcpServers": {
    "modelslab-v7": {
      "url": "https://modelslab.com/mcp/v7",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
```

- Documentation: https://docs.modelslab.com/mcp-web-api/overview

### Agent Skills

Install skill files directly into AI coding agents:

```bash
npx skills add modelslab/skills --all                          # All skills
npx skills add modelslab/skills --skill image-generation       # Specific skill
npx skills add modelslab/skills --all -a claude-code -a cursor # Target agents
```

- GitHub: https://github.com/ModelsLab/skills
- Documentation: https://docs.modelslab.com/agent-skills

### SDKs

- Python: `pip install modelslab`
- TypeScript: `npm install modelslab`
- PHP: `composer require modelslab/modelslab`
- Go: `go get github.com/modelslab/modelslab-go`
- Dart: `dart pub add modelslab`

## Links

- [Model Playground](https://modelslab.com/models/alibaba_cloud/wan3.0-r2v)
- [API Documentation](https://docs.modelslab.com)
- [ModelsLab Platform](https://modelslab.com)