image-generator

Generate and edit images using Gemini AI models with text prompts.

11|Updated Dec 26, 2025

Search Tags:#image generation #logo design #image editing #image processing #AI image creation

Ready to run

npx skills add https://github.com/ethanolivertroy/my-agent-stuff --skill image-generator-ethanolivertroy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: image-generator
Source: https://github.com/ethanolivertroy/my-agent-stuff/tree/main/skills/image-generator
Command: npx skills add https://github.com/ethanolivertroy/my-agent-stuff --skill image-generator-ethanolivertroy

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the need for a versatile tool to generate, edit, and refine images using AI-driven Gemini models.

Core Features & Use Cases

Image Generation: Convert text descriptions into high-quality images.
Image Editing: Edit existing images using text prompts, adding or removing elements.
Logo Creation: Design custom logos with specific design requirements.
Use Case: If you need to create a product mockup or edit a promotional image for social media, this Skill can help you achieve your goals.

Quick Start

To generate an image based on a description, use the command: /image-generator "create a landscape photo at sunset with a silhouette of mountains".

Frequently Asked Questions about image-generator

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

FAQPage Schema

How do I generate images from text descriptions using Gemini AI?▼

To generate images from text using Gemini AI, you provide a descriptive text prompt and the system handles the text-to-image conversion to create a high-quality visual output.

Can I edit existing images with text prompts to add or remove elements?▼

Yes, you can perform semantic image editing by providing text prompts to add or remove elements, allowing the Gemini AI to process and modify your existing images based on your instructions.

Do I need a Gemini API key to use AI image creation and logo design?▼

Yes, a valid Gemini API key is required to use AI image creation and logo design features. You must configure this dependency before generating images, editing visuals, or creating custom logos.

What is the best way to create a custom logo with specific design requirements?▼

The best way to create a custom logo is to provide specific design requirements as a text prompt. The Gemini AI processes your design constraints and generates a tailored logo image matching your criteria.

Does Gemini image processing support multi-image input and style transfer?▼

Yes, Gemini image processing supports multi-image input, style transfer, and image composition, allowing you to handle multiple visual inputs simultaneously to merge styles into a high-resolution output.