What is required to use the Gemini ImageGen skill?

You need a valid Gemini API key from Google AI Studio (MakerSuite) set as an environment variable (GEMINI_API_KEY) and the @google/generative-ai package installed.

Can I edit existing images with this skill?

Yes, the skill includes an 'edit' command that uses Gemini's vision and generation capabilities to modify existing source images based on your natural language instructions.

Which AI models does this skill utilize?

It primarily uses Google's latest models, including gemini-2.0-flash-exp for processing and imagen-3.0-generate-001 for high-quality image generation tasks.

What image formats are supported?

The skill supports common web formats including PNG, JPEG, and WebP, with automatic format detection based on your specified output file extension.

Is it possible to combine multiple images into one?

Yes, the 'compose' script allows you to intelligently blend 2-4 images into various layouts such as grids, horizontal banners, or vertical stacks using AI-assisted positioning.

Gemini Image Generator

Name: Gemini Image Generator
Author: hirefrank

byhirefrank

•

Herramientas de Diseño

Generates, edits, and composes high-quality visual content using Google's Gemini AI API directly within your development workflow.

Acerca de

The Gemini ImageGen skill integrates Google's advanced generative AI capabilities into Claude Code, allowing developers to handle visual tasks without leaving their terminal. It enables text-to-image generation, natural language image editing, and intelligent multi-image composition. By leveraging models like Imagen 3.0, this skill simplifies the creation of UI mockups, marketing assets, and documentation illustrations, providing a powerful bridge between code and design for rapid prototyping and automated content creation.

Características Principales

Text-to-image generation using Google's Imagen 3.0 models
Multi-image composition with grid, horizontal, and vertical layouts
Customizable output dimensions and support for PNG, JPEG, and WebP
2 GitHub stars
Natural language image editing and style transformations
Direct integration with local development scripts via tsx

Casos de Uso

Automating the creation of social media banners and marketing graphics
Creating technical illustrations and diagrams for project documentation
Generating UI/UX mockups and placeholder assets during frontend development

Acerca de

Características Principales

Text-to-image generation using Google's Imagen 3.0 models
Multi-image composition with grid, horizontal, and vertical layouts
Customizable output dimensions and support for PNG, JPEG, and WebP
2 GitHub stars
Natural language image editing and style transformations
Direct integration with local development scripts via tsx

Casos de Uso

Automating the creation of social media banners and marketing graphics
Creating technical illustrations and diagrams for project documentation
Generating UI/UX mockups and placeholder assets during frontend development