Qwen Image Gen for Openclaw

A professional-grade image generation skill powered by Alibaba Cloud's Qwen models for high-fidelity text-to-image creation.

lanlan314
v1.0.0
Mar 31, 2026
0
681
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install qwen-image-gen-lan

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install qwen-image-gen-lan 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 Gen?

The Qwen Image Gen skill integrates Alibaba Cloud's powerful Qwen-Image multimodal models into your workflow. This skill enables AI agents to generate high-resolution images based on natural language descriptions in both Chinese and English. By leveraging the DashScope API, it provides access to specialized models like qwen-image-2.0-pro for superior text rendering and qwen-image-max for photorealistic results.

Designed for versatility, this Openclaw Skills integration allows users to specify precise technical parameters including aspect ratios, negative prompts, and intelligent prompt extension. It is an essential tool for developers and creators needing programmatic access to cutting-edge generative AI imagery within their autonomous agent environments.

Qwen Image Gen Use Cases

  • Creating marketing assets or social media visuals directly via AI agent commands.
  • Prototyping UI/UX designs with specific resolution and aspect ratio requirements.
  • Generating photorealistic backgrounds or textures for creative projects.
  • Automating the generation of custom illustrations based on textual content updates.

How Qwen Image Gen Works

  1. The system verifies the presence of the DASHSCOPE_API_KEY environment variable to ensure authorized access.
  2. A JSON request body is constructed using the user's prompt and desired parameters like model choice and image size.
  3. The skill executes a synchronous API call to the DashScope multimodal generation endpoint.
  4. It parses the resulting JSON response to extract the temporary image URL.
  5. The final image URL is returned to the user or passed to the next agent in the workflow.

Qwen Image Gen Setup

To use this skill, ensure you have an active Alibaba Cloud DashScope account and set your API key:

# Set your API Key environment variable
export DASHSCOPE_API_KEY="your_api_key_here"

You can then trigger the skill via a standard API request or through an Openclaw Skills enabled agent.

Qwen Image Gen Data Schema & Taxonomy

The skill interacts with the DashScope API and returns structured data as follows:

Data Point Type Description
image_url String A temporary public URL for the generated image (valid for 24 hours).
usage Object Metadata including width, height, and image count.
request_id String Unique identifier for tracking and debugging requests.
finish_reason String Status indicator (e.g., 'stop' upon successful completion).

Qwen Image Gen Advanced Features

  • Support for negative prompts to exclude unwanted elements like low resolution or anatomical distortions.
  • Intelligent prompt extension to automatically enhance short user descriptions for better visual output.
  • Multi-model selection allowing users to toggle between speed (qwen-image-2.0) and maximum quality (qwen-image-2.0-pro).
  • Custom aspect ratio support ranging from standard 1:1 square images to 16:9 widescreen and 9:16 vertical formats.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*