← Back to Skills Marketplace
robin797860

Qwen Image

by Robin797860 · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
9496
Downloads
7
Stars
130
Active Installs
1
Versions
Install in OpenClaw
/install qwen-image
Description
Generate images using Qwen Image API (Alibaba Cloud DashScope). Use when users request image generation with Chinese prompts or need high-quality AI-generated images from text descriptions.
Usage Guidance
Install only if you are comfortable sending prompts and generation settings to Alibaba Cloud DashScope. Use a dedicated DashScope API key, avoid passing real keys directly on the command line, do not include secrets or regulated data in prompts, avoid --no-verify-ssl except in a controlled proxy setup, and save files only to paths you intentionally choose.
Capability Analysis
Type: OpenClaw Skill Name: qwen-image Version: 1.0.0 The skill is generally benign, performing image generation via the Alibaba Cloud DashScope API as described. However, the `scripts/generate_image.py` file includes a `--no-verify-ssl` flag which, when enabled, disables SSL certificate verification for both the API request and image download. While the `SKILL.md` documentation mentions this as a feature for corporate proxies, disabling SSL verification is a high-risk capability that could expose the agent to Man-in-the-Middle attacks, making the skill suspicious despite the lack of clear malicious intent.
Capability Assessment
Purpose & Capability
The artifacts coherently implement the stated purpose: send a prompt to Alibaba Cloud DashScope, return a generated image URL, and optionally save the image when a filename is provided.
Instruction Scope
Runtime instructions are focused on generating and displaying images; the docs mention API keys and a TLS-disabling flag, but there is no hidden role change, broad local indexing, background execution, or unrelated authority.
Install Mechanism
Installation requires uv and a Python requests dependency; this is proportionate for a small API wrapper, though dependencies are not fully pinned.
Credentials
Outbound network access and a DashScope API key are expected for this purpose. The script itself reads only a CLI key or DASHSCOPE_API_KEY, while the documentation also tells users where they may obtain keys from local OpenClaw config.
Persistence & Privilege
There is no persistence, privilege escalation, or background worker. Local file writing occurs only when the user supplies a filename, so users should choose the output path carefully.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install qwen-image
  3. After installation, invoke the skill by name or use /qwen-image
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the qwen-image skill. - Generates high-quality AI images using the Alibaba Cloud Qwen Image API (DashScope). - Supports both Chinese and English text prompts. - Provides various image sizes and advanced options such as negative prompts and watermarking. - Returns image URLs for easy viewing; local saving is available by request. - Automatic extraction and markdown rendering of images from script output.
Metadata
Slug qwen-image
Version 1.0.0
License
All-time Installs 358
Active Installs 130
Total Versions 1
Frequently Asked Questions

What is Qwen Image?

Generate images using Qwen Image API (Alibaba Cloud DashScope). Use when users request image generation with Chinese prompts or need high-quality AI-generated images from text descriptions. It is an AI Agent Skill for Claude Code / OpenClaw, with 9496 downloads so far.

How do I install Qwen Image?

Run "/install qwen-image" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Qwen Image free?

Yes, Qwen Image is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Qwen Image support?

Qwen Image is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Qwen Image?

It is built and maintained by Robin797860 (@robin797860); the current version is v1.0.0.

💬 Comments