skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

qwen-image-2

Generate and edit images with Alibaba Qwen-Image-2.0 models via the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#poster design#image generation#image editing#text-to-image#qwen#inference.sh#alibaba
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill qwen-image-2-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qwen-image-2
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/qwen-image-2
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill qwen-image-2-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating custom images, posters with accurate text rendering, or multi-reference image edits typically requires design tools or manual prompting of separate services. This Skill provides direct CLI access to Alibaba's Qwen-Image-2.0 models for text-to-image generation and multi-image editing. ## Core Features & Use Cases - Text-to-Image Generation: Create images from prompts with control over resolution, count, seed, and negative prompts using the fast Qwen-Image-2.0 model. - Professional Text Rendering: Use Qwen-Image-2.0-Pro for posters and text-heavy designs where exact quoted text, fonts, and positioning matter. - Multi-Image Editing: Supply 1-3 reference images to combine subjects, clothing, and poses into a new composition. - Use Case: Generate a promotional poster with the exact headline "Summer Sale!" in bold red text over a beach background at 1024x1536 resolution using the Pro model. ## Quick Start Ask the AI to generate an image of a futuristic cityscape at sunset using the qwen-image-2 model via the belt CLI.

Frequently Asked Questions about qwen-image-2

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

FAQPage Schema
How do I generate images with Qwen-Image-2.0 from the command line?▼

Run belt app run alibaba/qwen-image-2 with a JSON input containing your prompt. You must first install the inference.sh belt CLI and authenticate with belt login before running any app.

What is the difference between Qwen-Image-2.0 and Qwen-Image-2.0-Pro?▼

Qwen-Image-2.0 is faster and suited for general use, while Qwen-Image-2.0-Pro offers professional text rendering, finer realism, and stronger semantic adherence. Use the Pro model for posters and text-heavy designs.

Can Qwen-Image-2.0 edit existing images with references?▼

Yes, the model accepts 1-3 reference images via the reference_images parameter with image URIs. You can combine elements across images, such as applying clothing from one image to a person in another.

What resolution limits does Qwen-Image-2.0 support?▼

Width and height each range from 512 to 2048 pixels, and total pixels must fall between 512x512 and 2048x2048. Prompts are limited to 800 characters and negative prompts to 500 characters.

How do I get reproducible results from Qwen image generation?▼

Set the seed parameter to a fixed integer between 0 and 2147483647 in your input JSON. Using the same seed with the same prompt produces consistent output across runs.

Related Skills

Explore More Design & Creative Skills→
inference-shinference-sh
723

gpt-image

Generate and edit images with OpenAI GPT-Image-2 via the inference.sh CLI.

Official
Basic
sureshkushwaha123sureshkushwaha123

media-generation

Generate images, videos, and stock images from text prompts.

Community
Intermediate
inference-shinference-sh
723

elevenlabs-tts

Generate speech audio from text using ElevenLabs voices via the inference.sh CLI.

Official
Basic
agentic-inagentic-in
577

Stable Diffusion

Generate images from text prompts using Stable Diffusion via HuggingFace Diffusers.

Official
Advanced