← Back to Skills Marketplace
zhouweico

qwen-image-gen

by Wei Zhou · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
135
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install qwen-image-gen
Description
基于阿里云百炼 Qwen-Image 文生图模型的生图 skill。支持同步生成、异步任务轮询、下载生成结果到本地。 当用户需要根据提示词生成图片、批量出图、指定尺寸/比例,或继续查询已有图片生成任务时,使用此 skill。
Usage Guidance
This skill runs a local Node script that will call Aliyun's DashScope (Qwen-Image) APIs and download generated PNGs to an outputs/ directory. Before installing/providing credentials: 1) confirm the DASHSCOPE_API_KEY is the correct key for the intended Aliyun region (the README warns region keys/URLs cannot be mixed), 2) review the included scripts (they are present and readable) and run in an isolated environment if unsure, 3) store the API key in an environment variable rather than committing it to a repo or config file, and 4) be aware that generating images incurs cost per image per the pricing table. If you do not trust the source, do not provide high-privilege credentials or run the script on sensitive systems.
Capability Analysis
Type: OpenClaw Skill Name: qwen-image-gen Version: 0.1.0 The skill bundle provides a legitimate implementation for generating images via Alibaba Cloud's Qwen-Image API. The core logic in `scripts/qwen-image-gen.js` handles API authentication, task polling, and image downloading with proper filename sanitization to prevent path traversal. No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
The skill is an image-generation client for Aliyun's Qwen-Image service. It requires Node and a DASHSCOPE_API_KEY, references dashscope.aliyuncs.com as the API host, and includes code to call the documented endpoints — these are appropriate for the described purpose.
Instruction Scope
SKILL.md instructs the agent to set DASHSCOPE_API_KEY, optionally use config.json, run the provided Node script, and download outputs to outputs/. The instructions only reference files and env vars relevant to configuring and running the image-generation flow (no unrelated file reads or external endpoints).
Install Mechanism
There is no install spec (instruction-only behavior plus an included Node script). The script relies on Node >=18 and built-in fetch; no external download/install from untrusted URLs or package registries occurs. Risk from install mechanism is low.
Credentials
The only required credential is DASHSCOPE_API_KEY (primaryEnv). That matches the documented API usage. The code may also read optional environment keys (e.g., QWEN_IMAGE_MODEL) and a local config.json; these are reasonable and proportional to configuration needs.
Persistence & Privilege
The skill does not request permanent always:true inclusion and does not attempt to modify other skills or system-wide settings. It runs as a local Node script and writes outputs to a local outputs/ directory as expected.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install qwen-image-gen
  3. After installation, invoke the skill by name or use /qwen-image-gen
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Qwen-Image-Gen Skill 1.0.0 - Initial release of a skill for generating images using Alibaba Cloud Qwen-Image API. - Supports both synchronous and asynchronous image generation, with automatic mode selection based on the chosen model. - CLI tool to generate images with prompt, batch generation, specify size/ratio, perform dry-run checks, and manage async tasks. - Images are automatically downloaded as PNG to a local folder upon success. - Detailed parameter controls and model selection for balancing quality, speed, and cost. - Price hints and task/result links handling note.
Metadata
Slug qwen-image-gen
Version 0.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is qwen-image-gen?

基于阿里云百炼 Qwen-Image 文生图模型的生图 skill。支持同步生成、异步任务轮询、下载生成结果到本地。 当用户需要根据提示词生成图片、批量出图、指定尺寸/比例,或继续查询已有图片生成任务时,使用此 skill。 It is an AI Agent Skill for Claude Code / OpenClaw, with 135 downloads so far.

How do I install qwen-image-gen?

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

Is qwen-image-gen free?

Yes, qwen-image-gen is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does qwen-image-gen support?

qwen-image-gen is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created qwen-image-gen?

It is built and maintained by Wei Zhou (@zhouweico); the current version is v0.1.0.

💬 Comments