Can I edit existing images or just generate new ones?

You can do both. The skill supports image editing, including adding/removing elements, background changes, and product placement using reference images.

Do I need my own API keys?

Yes, you need an OPENAI_API_KEY for GPT models or a GOOGLE_API_KEY for Gemini models configured in your environment variables.

What is the maximum resolution supported?

Google Gemini Nano Banana Pro supports up to 4K resolution for high-quality professional outputs.

Which AI models does this skill support?

It supports OpenAI GPT Image models (1.5, 1, and 1-mini) and Google Gemini models (Nano Banana and Nano Banana Pro).

Does it support transparent backgrounds?

Yes, the OpenAI GPT Image models specifically support generating images with transparent backgrounds using the --background transparent flag.

AI Image Generation & Editing

Name: AI Image Generation & Editing
Author: michaelboeding

bymichaelboeding

•

Design Tools

Generates and modifies high-quality images using OpenAI and Google Gemini models directly within your AI development workflow.

This skill empowers Claude to perform complex image-related tasks, ranging from basic text-to-image generation to advanced multi-image compositing and professional product placement. By leveraging state-of-the-art models like Google Gemini Nano Banana Pro and OpenAI GPT Image 1.5, it provides an interactive workflow that guides users through selecting aspect ratios, resolutions, and styles. Whether you need to create marketing assets, edit existing photos with masks, or perform artistic style transfers, this skill automates the technical prompting and API execution while maintaining high creative fidelity.

Key Features

01Support for various aspect ratios, 4K resolution, and transparent backgrounds

029 GitHub stars

03Multi-model support for OpenAI GPT Image and Google Gemini Nano Banana Pro

04Advanced image editing including inpainting, object addition/removal, and background replacement

05High-fidelity product placement and multi-image compositing

06Interactive step-by-step requirement gathering for precision results

Use Cases

01Applying artistic styles or consistent branding to a set of photographs using style transfer capabilities

02Creating high-quality marketing assets and product mockups from text descriptions or reference photos

03Iteratively editing existing images by adding or removing elements via natural language commands

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add michaelboeding/skills image-generation

For use in Claude.ai and ChatGPT

Download Skill