A professional AI image generation and editing skill utilizing the Qwen model via DashScope API for seamless text-to-image and image-to-image workflows.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install qwen-skill
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 qwen-skill 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 Qwen Image Skill?
The Qwen Image skill is a technical implementation designed for the Openclaw Skills framework, enabling AI agents to interact with the DashScope API for advanced visual content creation. It supports a variety of operations including high-fidelity text-to-image generation, single-image style transfers, and complex multi-image fusion using up to three input sources.
Built for reliability and automation, this skill bypasses traditional chat-based image limitations by executing local Python scripts. It emphasizes strict runtime behaviors, such as automatic media downloading, region-based endpoint switching, and structured media reference outputs, ensuring that generated content is stored locally and managed efficiently within a developer's infrastructure.
Qwen Image Skill Use Cases
- Creating cinematic high-resolution visuals from descriptive text prompts for marketing or prototyping.
- Transforming existing images into new artistic styles like watercolor or sketches while maintaining composition.
- Fusing multiple input images to create complex visual edits or blended concepts.
- Automating local media outbound pipelines for team communication platforms like Feishu or Slack.
How Qwen Image Skill Works
- The AI agent reads the SKILL.md definition to identify required environment variables and script paths.
- The agent constructs a Python execution command based on the user's intent (text2img or img2img).
- The script calls the DashScope API using the provided model (e.g., qwen-image-2.0-pro).
- Generated images are immediately downloaded to a local temporary directory to avoid expired URL issues.
- Files are published to a designated outbound directory, and a
.view.htmlpreview is generated. - The script emits a specific MEDIA_REF, which the agent parses to provide a final, structured media response.
Qwen Image Skill Setup
Install the required dependencies using pip:
pip3 install -r {baseDir}/requirements.txt
Configure your environment variables or create a .env file:
export DASHSCOPE_API_KEY="your_api_key"
export DASHSCOPE_REGION="sg" # Choose 'sg' for Singapore or 'bj' for Beijing
Define your outbound media directory to integrate with Openclaw Skills:
export OPENCLAW_MEDIA_OUTBOUND_DIR="~/.openclaw/media/outbound"
Qwen Image Skill Data Schema & Taxonomy
The skill manages data through a structured local file system and environment-based taxonomy:
| Component | Description |
|---|---|
| Out-Dir | Local storage for raw downloaded images and temporary processing files. |
| Publish-Dir | Public-facing or outbound directory for serving media to external interfaces. |
| .view.html | Automatically generated preview pages to reduce heavy markdown image rewrites. |
| Media Ref | A structured MEDIA:<path-or-url> string used for final assistant responses. |
Qwen Image Skill Advanced Features
- Multi-image fusion supporting 1 to 3 concurrent input images for complex editing.
- Automatic region-based failover for API keys across different geographic endpoints.
- Support for multiple input formats including local file paths, public URLs, and base64 encoded strings.
- Custom media outbound configurations and static URL mapping for Nginx integration.
- Flexible output formatting options like
--emit-media-reffor optimized messaging in Control UIs.
SKILL.md
Loading
Related Openclaw Skills
Configure Tools
A professional-grade configuration skill for managing tool access policies, execution security, and agent capabilities within the Openclaw ecosystem.
Site Inspector
An offline-first reference tool providing instant access to DevTools best practices, implementation patterns, and debugging guides.
17CE Global Website Speed Test
A real-time global performance monitoring tool that tracks website speed, HTTP response times, and AI model availability via 17CE's distributed node network.
SilicaClaw Network Config
A specialized skill for inspecting and modifying SilicaClaw runtime network modes and public discovery states.
System Hardener
A comprehensive local reference tool providing instant access to system hardening concepts, implementation patterns, and security best practices.
Contact Page Generator
A specialized tool for designing, auditing, and optimizing contact pages and lead capture forms to maximize user engagement and conversions.
Featured*
