Zimage Generation

This is a straightforward wrapper around ModelScope's Z-Image API that lets you generate images from text prompts via command line. You'd reach for it if you specifically want to use ModelScope's infrastructure rather than other image generation services. The setup is flexible with three API key methods, from hardcoding it in the script to using environment variables, which is nice for different workflows. One heads up: there's a potential gotcha where you need to bind an Alibaba Cloud account to your ModelScope profile before the API will work, which isn't obvious until you hit a 401 error. It's a clean, single-purpose tool if ModelScope is already in your stack.

skills.sh installs: 872
GitHub stars: 13
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add toolsai/free-zimage-skills --skill zimage-generation --agent claude-code

Installs into .claude/skills of the current project.

Files

Z-Image Generation Skill

This skill allows you to generate images using the Z-Image model via the ModelScope Inference API.

When to Use

Use this skill when:

The user requests to generate an image using "Zimage", "zimage:", or "ModelScope".
The user inputs a command like zimage: <prompt> or zimage <prompt>.
The user wants to use their configured ModelScope API key for image generation.

Usage

The skill provides a Python script scripts/generate_zimage.py to handle the API interaction.

Prerequisites

Python 3 with requests installed.
API Key Setup (Choose one):
- Method A (Easiest for beginners): Open scripts/generate_zimage.py and paste your key into the DEFAULT_API_KEY variable at the top.
- Method B (Temporary): Pass via command line: --api-key your_token
- Method C (Recommended Project Setup): Create a new text file named .env in the same folder as the script (scripts/).
  - Content of the file should be: MODELSCOPE_API_TOKEN="your_key_here"