# MiniMax H3 Reference2Video

> AI model for generating video content

## Overview

- **Model ID**: `h3-minimax-r2v`
- **Category**: video
- **Provider**: modelslab
- **Source Type**: Open Source Model
- **Status**: model_ready
- **Screenshot**: `https://assets.modelslab.ai/generations/d0e21734-a16e-49ae-9f79-b3d3b4d17496.png`

## 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/v6/video/img2video`
- **Method**: POST

### Parameters

- **`prompt`** (required): Text prompt for video generation. Refer to reference assets by their modality and order in the reference lists: Image 1, Image 2, Video 1, Audio 1, and so on.
  - Type: textarea

- **`Duration`** (required): The duration of the video in seconds. Default value: 5
  - Type: number (range: 5-15)

- **`Resolution`** (optional): 
  - Type: textarea

- **`init_image`** (required): URLs of subject/style reference images, referenced in the prompt as Image 1, Image 2, and so on.
  - Type: array

- **`init_video`** (required): 
  - Type: array

- **`init_audio`** (required): URLs of reference audio clips (2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Audio 1, Audio 2, and so on. Audio cannot be the only reference input; provide at least one reference image or video with it. Reference images, videos, and audio clips must add up to at most 12 files.
  - Type: array

- **`model_id`** (optional): 
  - Type: text

## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://modelslab.com/api/v6/video/img2video \
  --header "Content-Type: application/json" \
  --data '{
    "key": "YOUR_API_KEY",
    "model_id": "h3-minimax-r2v",
    "prompt": "Create a cinematic continuous sequence using the storyboard as the visual reference. Keep the character, face, clothing, environment and visual style consistent. Animate each shot naturally: the ronin wakes and looks toward the smoke, walks slowly through the abandoned village, notices the figure in the fog, draws his katana, then suddenly charges forward and strikes. After the attack, slow the movement as he examines the glowing symbols appearing on his sword. He raises the sword toward the stormy sky as lightning builds, then walks toward the distant fortress as the clouds begin to clear. Smooth cinematic camera movement, natural body motion, realistic hair and clothing movement, atmospheric fog, smoke and rain. Epic Japanese fantasy film aesthetic. Add subtle cinematic orchestral background music that gradually builds during the confrontation and becomes powerful as the fortress is revealed. ",
    "Duration": "5",
    "Resolution": "768"
  }'
```

### Python

```python
import requests

response = requests.post(
    "https://modelslab.com/api/v6/video/img2video",
    headers={
        "Content-Type": "application/json"
    },
    json={
        "key": "YOUR_API_KEY",
        "model_id": "h3-minimax-r2v",
        "prompt": "Create a cinematic continuous sequence using the storyboard as the visual reference. Keep the character, face, clothing, environment and visual style consistent. Animate each shot naturally: the ronin wakes and looks toward the smoke, walks slowly through the abandoned village, notices the figure in the fog, draws his katana, then suddenly charges forward and strikes. After the attack, slow the movement as he examines the glowing symbols appearing on his sword. He raises the sword toward the stormy sky as lightning builds, then walks toward the distant fortress as the clouds begin to clear. Smooth cinematic camera movement, natural body motion, realistic hair and clothing movement, atmospheric fog, smoke and rain. Epic Japanese fantasy film aesthetic. Add subtle cinematic orchestral background music that gradually builds during the confrontation and becomes powerful as the fortress is revealed. ",
        "Duration": "5",
        "Resolution": "768"
    }
)

print(response.json())
```

### JavaScript

```javascript
fetch("https://modelslab.com/api/v6/video/img2video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "key": "YOUR_API_KEY",
    "model_id": "h3-minimax-r2v",
    "prompt": "Create a cinematic continuous sequence using the storyboard as the visual reference. Keep the character, face, clothing, environment and visual style consistent. Animate each shot naturally: the ronin wakes and looks toward the smoke, walks slowly through the abandoned village, notices the figure in the fog, draws his katana, then suddenly charges forward and strikes. After the attack, slow the movement as he examines the glowing symbols appearing on his sword. He raises the sword toward the stormy sky as lightning builds, then walks toward the distant fortress as the clouds begin to clear. Smooth cinematic camera movement, natural body motion, realistic hair and clothing movement, atmospheric fog, smoke and rain. Epic Japanese fantasy film aesthetic. Add subtle cinematic orchestral background music that gradually builds during the confrontation and becomes powerful as the fortress is revealed. ",
    "Duration": "5",
    "Resolution": "768"
  })
})
.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 "h3-minimax-r2v"                       # Find this model
modelslab models detail --id h3-minimax-r2v                    # Get model details
modelslab generate image --prompt "..." --model h3-minimax-r2v  # Generate with model
modelslab config set generation.default_model h3-minimax-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/modelslab/h3-minimax-r2v)
- [API Documentation](https://docs.modelslab.com)
- [ModelsLab Platform](https://modelslab.com)