qianwen-image-generation

Generate and edit images using Wan and Qwen Image models.

67|4|Updated May 9, 2026
One-click install
npx skills add https://github.com/QianWen-AI/qianwen-ai --skill qianwen-image-generation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qianwen-image-generation
Source: https://github.com/QianWen-AI/qianwen-ai/tree/main/skills/image/qianwen-image-generation
Command: npx skills add https://github.com/QianWen-AI/qianwen-ai --skill qianwen-image-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Generates and edits images using Wan and Qwen Image models, enabling text-to-image generation, style transfer, subject consistency, and interleaved text-image output.

Core Features & Use Cases

  • Text-to-image generation
  • Image editing with style transfer and subject consistency
  • Interleaved text-image output for tutorials or step-by-step guides
  • Reference-image support (0–9 images) and sequential multi-image generation
  • Easy integration with internal scripts and prompts for quick starts

Quick Start

Run the script with a simple prompt to generate an image, for example a cozy flower shop with a wooden door.

Frequently Asked Questions about qianwen-image-generation

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

FAQPage Schema
How do I generate images from text using Qwen models?

To start text-to-image generation, run the provided script with a simple descriptive prompt. The skill leverages Wan and Qwen Image models to translate your text input into visual output.

Can I use reference images for style transfer and subject consistency?

Yes, you can use reference images to achieve style transfer and subject consistency. The skill supports uploading zero to nine reference images to guide the visual output and maintain thematic coherence.

Does this skill support interleaved text-image output for tutorials?

Yes, it supports interleaved text-image output to create tutorials or step-by-step guides. This allows you to generate sequential visual content seamlessly mixed with descriptive text.

What is the best way to edit an existing image with Qwen?

The best way to edit an existing image is by using the script's upload and resolution flow, which accepts local files or URLs. You can apply style transfer and text rendering modifications directly through Qwen models.

How many reference images can I provide for sequential multi-image generation?

You can provide between zero and nine reference images for sequential multi-image generation. This allows for complex visual tasks while maintaining subject consistency across multiple generated outputs.