gemini

Generate and edit images via Google's Gemini API.

Updated Dec 31, 2025
One-click install
npx skills add https://github.com/JerichoCruz/google-image-gen-claude-code --skill gemini-jerichocruz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini
Source: https://github.com/JerichoCruz/google-image-gen-claude-code/tree/main/.claude/skills/gemini
Command: npx skills add https://github.com/JerichoCruz/google-image-gen-claude-code --skill gemini-jerichocruz

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill allows users to generate new images, edit existing ones, and perform complex image transformations like face swaps and style transfers using Google's Gemini AI, all through a conversational interface.

Core Features & Use Cases

  • Text-to-Image Generation: Create images from descriptive text prompts.
  • Image Editing: Modify existing images (e.g., change lighting, add objects).
  • Advanced Transformations: Perform face swaps, pose transfers, and style transfers using multiple input images.
  • Conversational Refinement: Iteratively improve image generations through dialogue.
  • Use Case: A user wants to create a unique avatar for their profile. They can describe their desired character, and the Skill will generate it, allowing for further refinements like changing the background or adding accessories.

Quick Start

Use the gemini skill to generate an image of a friendly robot in a sunlit workshop.

Frequently Asked Questions about gemini

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

FAQPage Schema
How do I use Gemini AI for image generation and editing?

Gemini AI image generation and editing is driven through a conversational interface that processes text prompts to create new images or modify existing ones. You can iteratively refine outputs like lighting or background changes through dialogue.

Can I perform a face swap or pose transfer using text prompts?

Face swaps and pose transfers are supported using multiple input images as references. The Gemini API processes these reference images alongside your text instructions to execute complex visual transformations.

Do I need a Gemini API key to generate AI art?

A Gemini API key is required to authenticate and execute deterministic image generation tasks. You also need Python 3.8 or higher installed in your environment to run the necessary scripts.

What is the best way to do style transfer with multiple images?

Style transfer with multiple images is achieved by providing several reference inputs to the Gemini API. The Skill analyzes these references to apply the desired artistic style to your target image through conversational commands.

Does conversational image generation support iterative refinements?

Conversational image generation supports iterative refinements by allowing you to adjust outputs through dialogue. You can modify specific elements like backgrounds or accessories without restarting the entire prompt.

What are the limitations of using Gemini API for image transformations?

Gemini API image transformations require Python 3.8+ and a valid API key for execution. Complex tasks like multi-image style transfers depend entirely on the API's deterministic processing capabilities and your reference image quality.