gemini-image

Convert text prompts and image URLs into AI-generated artwork.

Updated Feb 22, 2026
One-click install
npx skills add https://github.com/wyhlovecpp/my-codex-settings --skill gemini-image-wyhlovecpp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-image
Source: https://github.com/wyhlovecpp/my-codex-settings/tree/main/skills/by-category/media/image-generation/gemini-image
Command: npx skills add https://github.com/wyhlovecpp/my-codex-settings --skill gemini-image-wyhlovecpp

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables users to generate high-quality images through AI based on their textual descriptions, simplifying the creative process.

Core Features & Use Cases

  • Text-to-Image Generation: Transform detailed text prompts into visual artwork or illustrations.
  • Image-to-Image Conversion: Modify or enhance existing images by referencing URLs and descriptions.
  • Use Case: Artists can quickly prototype visual concepts by describing scenes or characters in plain language and receiving corresponding images.

Quick Start

Ask the AI to generate or modify an image by providing a descriptive prompt or image URL along with your instructions.

Frequently Asked Questions about gemini-image

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

FAQPage Schema
How do I generate AI artwork from text prompts?

Text-to-image generation works by converting your detailed textual descriptions into visual artwork through API integration. You simply provide a descriptive prompt, and the AI constructs the image based on your instructions.

Can I modify an existing image using AI and a reference URL?

Yes, image-to-image conversion allows you to modify or enhance existing images by providing an image URL along with descriptive instructions. The AI processes the reference and your text to generate the updated artwork.

Do I need curl installed to use this text-to-image generation Skill?

Yes, curl is a required dependency for this text-to-image Skill, as it handles the API integration for prompt construction and image upload functionalities. Ensure curl is installed in your environment before use.

What's the best way to prototype visual concepts quickly using AI art?

The best way to prototype visual concepts is by describing scenes or characters in plain language to the AI. The Skill transforms these detailed text prompts into corresponding images, enabling fast visual content creation for artists.

Are there limitations when uploading image references for image-to-image conversion?

Image-to-image conversion requires providing a valid image URL and descriptive instructions to the AI. Ensure your image references are accessible via URL for the API integration to successfully process and modify the artwork.

Does gemini-image support both text-to-image and image-to-image tasks?

Yes, this Skill supports both text-to-image generation and image-to-image conversion. It handles API integration for prompt construction and image uploads, allowing users to create new artwork or modify existing images.