Qwen Image 2
Generates detailed, high-quality images from text prompts using the Qwen-Image-2 model for creative visualization.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add qwen-image-2 npx -- -y @trustedskills/qwen-image-2
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"qwen-image-2": {
"command": "npx",
"args": [
"-y",
"@trustedskills/qwen-image-2"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The qwen-image-2 skill enables AI agents to process and analyze images with advanced vision capabilities. It supports tasks such as image classification, object detection, and generating descriptive text from visual content.
When to use it
- To extract details from images for data analysis or documentation.
- For automating quality checks in manufacturing by identifying defects in product images.
- When creating accessible content by describing images for visually impaired users.
Key capabilities
- Image classification with high accuracy
- Object detection and localization within images
- Generating natural language descriptions of visual content
Example prompts
- "Describe the objects present in this image."
- "Identify any defects in the product shown."
- "What is the main subject of this photo?"
Tips & gotchas
- Ensure that input images are clear and well-lit for optimal results.
- Be aware that performance may vary based on the complexity and context of the visual content provided.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.