image-generation

Generate and edit images via OpenAI GPT Image and Google Gemini APIs.

24|2|Updated Dec 30, 2025

Search Tags:#image-generation #image-editing #multi-image #style-transfer #reference-images #AI-art #product-placement

Ready to run

npx skills add https://github.com/michaelboeding/skills --skill image-generation-michaelboeding

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: image-generation
Source: https://github.com/michaelboeding/skills/tree/main/skills/image-generation
Command: npx skills add https://github.com/michaelboeding/skills --skill image-generation-michaelboeding

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill enables rapid image creation and editing using AI models, removing the bottleneck of manual design for common visuals.

Core Features & Use Cases

Text-to-image generation: Create visuals from natural language prompts.
Image editing with references: Modify existing images using reference images or masks.
Product placement & style transfer: Add products to scenes and apply artistic styles.
Multi-image composition: Combine several images into a single, coherent scene.

Quick Start

Provide a descriptive prompt like "Design a product hero image for a coffee shop" to start generation. The agent will select a suitable model, aspect ratio, and output settings automatically.

Frequently Asked Questions about image-generation

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

FAQPage Schema

How do I generate images from text prompts using AI?▼

Text-to-image generation converts natural language descriptions into visual assets automatically. This Skill uses OpenAI GPT Image and Google Gemini APIs to create images from prompts—just describe what you need (e.g., "coffee shop hero image") and the agent selects the model, aspect ratio, and settings.

Can I edit existing images with AI and reference images?▼

Yes, image editing with references lets you modify existing images by providing reference visuals or masks as guides. This Skill combines reference images with AI models to apply changes while maintaining coherence with your source material.

What do I need to set up before using AI image generation?▼

You need API keys for OpenAI (OPENAI_API_KEY) and Google (GOOGLE_API_KEY) configured in your environment. The Skill runs local Python scripts that authenticate with these APIs to execute generation and editing workflows.

How do I combine multiple images into a single scene?▼

Multi-image composition merges several images into one coherent output. This Skill uses AI models to blend and integrate multiple source images while maintaining visual consistency and style alignment across the final result.

Can I apply artistic styles or add products to generated images?▼

Yes, style transfer applies artistic effects to images, and product placement adds items to scenes automatically. Both run through the same AI-powered workflows, letting you transform visuals or insert products without manual design work.

What's the best way to automate image creation for recurring design needs?▼

Automating image generation removes manual design bottlenecks by letting you run text-to-image workflows programmatically via scripts. This Skill handles aspect ratio selection and model routing, making batch or triggered generation practical for product visuals, marketing assets, or mock-ups.