A powerful skill for automating high-quality video generation using Alibaba Cloud PixVerse v5.6 models within the Model Studio ecosystem.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install aliyun-pixverse-generation
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 aliyun-pixverse-generation 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 Aliyun PixVerse Video Generation?
This skill enables developers to harness the Alibaba Cloud Model Studio PixVerse family for professional-grade video synthesis. It facilitates multiple generation modes including text-to-video, first-frame image-to-video, keyframe transitions, and multi-image reference workflows. By leveraging this Openclaw Skills component, users can programmatically create cinematic content with precise control over resolution, duration, and stylistic consistency.
Designed for integration into modern AI agent architectures, the skill provides a normalized interface for interacting with Alibaba Cloud's Aishi video generation engine. Whether you are building automated marketing pipelines or creative design tools, this Openclaw Skills implementation ensures robust task management and predictable video outputs through the DashScope API.
Aliyun PixVerse Video Generation Use Cases
- Automated text-to-video creation for social media and digital marketing campaigns.
- Generating seamless cinematic transitions between two specific keyframe images.
- Maintaining character or style consistency across multiple generated videos using up to seven image references.
- High-resolution video prototyping for rapid iteration in game development or film pre-visualization.
How Aliyun PixVerse Video Generation Works
- The user selects a specific PixVerse model variant (t2v, it2v, kf2v, or r2v) based on their input source.
- The skill prepares a normalized request payload including prompts, media URLs, and resolution parameters.
- An asynchronous POST request is sent to the DashScope synthesis endpoint, returning a unique task ID.
- The system initiates a polling cycle to monitor the task status through the Alibaba Cloud API.
- Upon completion, the skill retrieves the final video URL and saves the execution evidence to the local output directory.
Aliyun PixVerse Video Generation Setup
To use this Openclaw Skills package, ensure you have an active Alibaba Cloud account and a valid API key.
# Install the necessary DashScope SDK
python -m pip install dashscope
# Configure your environment with your API credentials
export DASHSCOPE_API_KEY="your_api_key_here"
# Validate the installation environment
mkdir -p output/aliyun-pixverse-generation
python -m py_compile skills/ai/video/aliyun-pixverse-generation/scripts/prepare_aishi_request.py
Aliyun PixVerse Video Generation Data Schema & Taxonomy
The skill organizes its operations through a structured request/response schema. Data and logs are stored in the output/aliyun-pixverse-generation/ directory for auditability within Openclaw Skills workflows.
| Parameter | Description | Supported Values |
|---|---|---|
model |
Target PixVerse model variant | t2v, it2v, kf2v, r2v |
prompt |
Textual description for generation | String (Required for most) |
resolution |
Output video quality | 360P, 540P, 720P, 1080P |
duration |
Total video length in seconds | 5, 8, or 10 |
media |
Input image sources | Array of image URLs/paths |
Aliyun PixVerse Video Generation Advanced Features
- Support for multi-image reference (r2v) allowing up to 7 images to maintain visual consistency for characters or artistic styles.
- Keyframe-to-video (kf2v) mode for precisely controlling the first and last frames of the generated sequence.
- Optional audio generation toggle to create complete multimedia assets directly from Openclaw Skills scripts.
- Flexible resolution mapping that automatically handles different requirements for size (t2v/r2v) versus resolution (it2v/kf2v).
- Comprehensive polling snapshots and task tracking for reliable asynchronous execution in multi-agent environments.
SKILL.md
Loading
Related Openclaw Skills
Lead Generation Pipeline
An autonomous 6-agent pipeline that researches industries, finds qualified businesses, and generates hyper-personalized outreach in a single API call.
Email Engine
A comprehensive email automation and AI communication suite designed for autonomous agents to manage outreach, classification, and replies.
Power User Pack
A premium collection of four essential tools designed to optimize memory, automate git workflows, and stabilize agent performance within the Openclaw Skills ecosystem.
Scheduling Engine
A programmatic scheduling engine designed for AI agents to manage staff availability, detect conflicts, and automate appointment booking.
Alibaba Cloud AnimateAnyone
An advanced AI motion-transfer skill that clones body movements from a template video onto a static character image using Alibaba Cloud Model Studio.
Aliyun EMO Portrait Video
An AI skill for generating high-expression portrait videos from static images and speech audio using Alibaba Cloud EMO-v1.
Featured*
