qwen-image

Generate images from text prompts via Alibaba Cloud's Qwen Image API.

47|4|Updated Feb 6, 2026
One-click install
npx skills add https://github.com/agentbay-ai/agentbay-skills --skill qwen-image-agentbay-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qwen-image
Source: https://github.com/agentbay-ai/agentbay-skills/tree/main/qwen-image
Command: npx skills add https://github.com/agentbay-ai/agentbay-skills --skill qwen-image-agentbay-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests>=2.31.0, and includes scripts (resource) components.

What problem does it solve?

This skill enables users to generate high-quality images from textual prompts using Alibaba Cloud's Qwen Image API, eliminating the need for manual artwork or hunting for visuals via multiple tools.

Core Features & Use Cases

  • Text-to-image generation with Qwen Image API supporting multiple models and customizable options (size, negative prompt, watermark, and prompt extend).
  • Returns an image URL by default and can download the image locally when requested, supporting both Chinese and English prompts.
  • Use Cases: Designers, marketers, and content creators can generate concept visuals for campaigns, UI mockups, product imagery, and social media assets on demand.

Quick Start

Provide a text prompt and run the generate_image.py script to obtain the image URL.

Frequently Asked Questions about qwen-image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images from text prompts using the Qwen Image API?

To generate images from text prompts, run the Python wrapper script with your descriptive prompt to call the Qwen Image API. The script returns an image URL by default and can download the image locally when requested, supporting both Chinese and English prompts.

Do I need a DashScope API key to generate AI art with this text-to-image tool?

Yes, you need a valid DashScope API key to generate AI art with this text-to-image tool. You must provide the key via the DASHSCOPE_API_KEY environment variable or pass it directly using the --api-key argument before running the script.

Can I customize image size and use negative prompts for text-to-image generation?

Yes, you can customize image size and use negative prompts for text-to-image generation. The Qwen Image API wrapper supports multiple models, allowing you to specify image dimensions, negative prompts, watermark options, and prompt extensions.

What is the best way to create UI mockups and concept visuals on demand?

The best way to create UI mockups and concept visuals on demand is using a text-to-image API wrapper. This skill enables designers and marketers to generate campaign visuals, product imagery, and social media assets directly from descriptive text prompts.

Does the Qwen Image API wrapper support downloading generated images locally?

Yes, the Qwen Image API wrapper supports downloading generated images locally. By default, the script returns a URL for the generated image, but it can automatically download the visual asset to your local machine when requested.

Why does my text-to-image generation fail when using the Python requests library?

Your text-to-image generation may fail if the required requests dependency is missing or the DashScope API key is invalid. Ensure the Python requests library is installed and a valid DASHSCOPE_API_KEY is configured in your environment.