An advanced video generation skill leveraging MiniMax Hailuo 2.3 to create cinematic AI videos from text prompts or static images.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install hailuo-video
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install hailuo-video using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Hailuo Video Generation (MiniMax 2.3)?
The Hailuo Video skill brings the state-of-the-art MiniMax Hailuo 2.3 model series to your AI agent, enabling the creation of high-fidelity video content. This skill allows users to transform natural language descriptions or existing images into dynamic, professional-grade videos. By utilizing Openclaw Skills, developers can easily switch between the Fast series for rapid iterations and the Standard series for peak visual quality, including 1080p Pro resolutions.
Whether you are building a marketing automation tool or a creative assistant, this skill provides the necessary hooks to generate 6-second or 10-second video clips with realistic movement and lighting. It integrates seamlessly into the MCP ecosystem, making high-end video synthesis accessible through simple tool calls.
Hailuo Video Generation (MiniMax 2.3) Use Cases
- Creating cinematic promotional clips from text descriptions for digital marketing campaigns.
- Animating product photos or character art into high-quality image-to-video sequences.
- Rapidly prototyping storyboards and visual concepts using the Fast model series.
- Generating high-resolution 1080p video assets for professional social media content using Openclaw Skills.
How Hailuo Video Generation (MiniMax 2.3) Works
- The user provides a text prompt or an image URL to the AI agent.
- The agent calls the submit_task tool with the appropriate model ID and parameters like resolution and duration.
- The system initiates the generation process via the MiniMax Hailuo 2.3 API and returns a unique task_id.
- The agent uses the get_task tool to poll the status of the generation (pending, processing, or completed).
- Once the status reaches completed, the final video URL and result metadata are returned for the user to download or view.
Hailuo Video Generation (MiniMax 2.3) Setup
To integrate this skill into your workflow, ensure your AI agent has access to the MCP runtime. You will need a valid API configuration for the fal-ai provider to access the MiniMax models.
# Example of submitting a text-to-video task
mcp call hailuo-video submit_task --model_id "fal-ai/minimax/hailuo-2.3/pro/text-to-video" --prompt "A cinematic shot of a cyberpunk city in the rain"
# Example of checking task status
mcp call hailuo-video get_task --task_id "YOUR_TASK_ID"
Hailuo Video Generation (MiniMax 2.3) Data Schema & Taxonomy
The skill organizes its operations through a task-based system described in the following schema:
| Property | Type | Description |
|---|---|---|
| model_id | string | The specific Hailuo 2.3 model variant used |
| task_id | string | Unique identifier for tracking the generation |
| status | string | The lifecycle state: pending, processing, completed, or failed |
| prompt | string | The descriptive text used to guide the video synthesis |
| image_url | string | The source image URL (required for image-to-video) |
| duration | string | Length of the video ("6" or "10" seconds) |
| result | object | Contains the final .mp4 URL and metadata upon success |
Hailuo Video Generation (MiniMax 2.3) Advanced Features
- Support for Pro versions offering full 1080p high-definition output.
- Dual-tier model selection (Fast vs. Standard) to optimize for either speed or visual fidelity.
- Integrated prompt_optimizer to automatically enhance user descriptions for better visual results.
- Flexible duration settings for Standard models, allowing for extended 10-second sequences.
- Fine-grained camera control support through descriptive prompt engineering within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Flux 2 Flash Image Generation
A high-performance AI skill for generating and editing photorealistic images with advanced text rendering and native editing capabilities.
Fashion Studio
An automated end-to-end workflow for creating professional e-commerce fashion photography and detail pages using specialized AI agent sub-delegation.
fal-ai Model Documentation Discovery
A specialized automation skill to extract all available model variants and documentation links from any fal.ai model page.
Fal Consumption Audit
A specialized auditing tool for reconciling Fal.ai API consumption with internal user billing records to ensure financial accuracy and detect usage anomalies.
Image Model Evaluation
An automated benchmarking suite for evaluating image generation models across dimensions like prompt adherence, style, and character consistency.
Hailuo Voice Synthesis and Design
A professional-grade audio synthesis skill powered by the Minimax API for high-fidelity text-to-speech, voice cloning, and natural language voice design.
Featured*
