gemini-image

Generate and edit images with Google's Gemini models via a zero-dependency Python CLI.

Updated Jun 16, 2026
One-click install
npx skills add https://github.com/BryceEWatson/claude-global-skills --skill gemini-image-bryceewatson
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-image
Source: https://github.com/BryceEWatson/claude-global-skills/tree/main/gemini-image
Command: npx skills add https://github.com/BryceEWatson/claude-global-skills --skill gemini-image-bryceewatson

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Generate and edit images with Google's Gemini models from a zero-dependency Python file. Use it as a Claude Code skill or standalone CLI to create visuals with reference images, multi-image outputs, and safety diagnostics.

Core Features & Use Cases

  • Reference-image input and image editing/composting from one or more references.
  • Multi-image output is saved as separate files when the API returns several images.
  • Auto-resolves the best available Gemini image model per API key, with safe defaults and offline fallback.
  • Works as Claude Code skill and standalone CLI for automation, batch tasks, dashboards.
  • Includes safety diagnostics (block/finish reasons) and model-listing capabilities.

Quick Start

Copy gemini-image into your Claude Code skills directory and run the script to generate or edit an image.

Frequently Asked Questions about gemini-image

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

FAQPage Schema
How do I generate images with Gemini AI from a text prompt?

You can generate images with Gemini AI by running a zero-dependency Python script that passes text prompts to Google's Gemini models. The script handles API calls, auto-selects the best model, and saves the output images locally.

Can I edit existing images using Gemini models?

Yes, you can edit existing images by providing reference images to the Python CLI. The script uses a generateContent-based workflow with input-images support to composite and modify visuals based on your text instructions.

Do I need to install Python dependencies to use the Gemini image generation script?

No, you do not need to install Python dependencies to use this script. It features a zero-dependency runtime, meaning it runs on any machine with standard Python installed without requiring additional package management.

Does the Gemini image CLI work as a Claude Code skill?

Yes, the Gemini image CLI works as a Claude Code skill. You copy the script into your Claude Code skills directory to integrate image generation and editing directly into your development workflow for automation and batch tasks.

How does the script handle multiple images returned by the Gemini API?

When the Gemini API returns multiple images, the script automatically saves each image as a separate file. This multi-image output handling ensures you receive all generated visuals without manual extraction or additional processing.

Why do my Gemini API image generation requests get blocked?

Your Gemini API image generation requests might get blocked due to safety filters. The script includes safety diagnostics that report block and finish reasons, helping you identify why the API rejected your specific text prompt or reference image content.