A professional AI tool for generating high-resolution images via Alibaba's wan2.6-t2i model with automated local storage and cloud hosting.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install wan
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 wan 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 Wan Image Generation?
Wan Image Generation is a specialized integration for Openclaw Skills that connects users to the Alibaba DashScope API. It utilizes the sophisticated wan2.6-t2i model to transform text prompts into high-quality illustrations, photos, and digital art. This skill is particularly valuable for developers and creators who need a streamlined workflow that moves beyond simple generation by automating the process of local file management and public cloud hosting.
By leveraging the power of Openclaw Skills, this tool handles the technical heavy lifting of API communication, local file system interaction, and third-party image hosting. Whether you need a quick concept sketch or a polished marketing asset, this skill provides a reliable bridge between advanced AI models and practical project deployment.
Wan Image Generation Use Cases
- Creating custom illustrations or concept art directly from a chat interface
- Generating and automatically hosting images for web development or blog posts
- Prototyping visual assets for UI/UX design workflows
- Automating the creation of social media content using advanced AI models
How Wan Image Generation Works
- The user provides a text prompt which is sent to the Alibaba DashScope API using the wan2.6-t2i model.
- The system processes the request, optionally applying prompt extension for improved visual fidelity.
- Upon successful generation, the skill extracts the temporary image URL from the API response.
- The image is immediately downloaded to the user's local Desktop directory to ensure data persistence.
- The local file is then uploaded to catbox.moe via its API to generate a permanent public URL for easy sharing.
Wan Image Generation Setup
To enable this capability within Openclaw Skills, you must first obtain an API key from Alibaba Cloud DashScope. Once you have your credentials, configure your environment:
# Set your API Key
export DASHSCOPE_API_KEY="your_dashscope_api_key_here"
# Ensure dependencies are available
sudo apt-get install curl python3 # For Linux
brew install curl # For macOS
Wan Image Generation Data Schema & Taxonomy
The skill manages image data through a structured sequence of local and remote storage. Data is organized as follows:
| Attribute | Description | Example |
|---|---|---|
| Model ID | The specific AI model used | wan2.6-t2i |
| Image Resolution | Supported dimensions using * separator | 12801280, 7201280 |
| Local Path | File system location for downloads | ~/Desktop/generated_image.png |
| Public Hosting | Final permanent URL provider | catbox.moe |
Wan Image Generation Advanced Features
- Support for multiple aspect ratios including square (1:1), portrait (9:16), and landscape (16:9)
- Integrated prompt_extend feature to automatically enhance user prompts for better AI interpretation
- Automatic watermark removal for clean, professional output
- Built-in error handling for API authentication issues and image URL expiration
SKILL.md
Loading
Related Openclaw Skills
OpenClaw Mem0 Plugin
A sophisticated memory integration that enables AI agents to remember user preferences, facts, and conversation history across multiple sessions.
MuskInsider Pro
A minimal HTTP service providing Elon Musk news briefings and demonstration payment integration for AI agents.
Triple Memory System with Baidu Embedding
A three-tier memory architecture combining Baidu-powered vector recall, structured Git-Notes, and local workspace search.
Thinking Model Enhancer
An advanced cognitive framework that optimizes AI decision-making through multi-stage processing and integrated memory feedback loops.
Frontend Design Extractor
An automated tool for extracting and documenting UI/UX design systems from frontend codebases while stripping away business logic.
Gemini Multimodal Media (Image/Video/Speech)
A powerful integration for Google Gemini that enables end-to-end multimodal workflows including image generation, video synthesis, and speech-to-text capabilities.
Featured*
