gemini-imagegen

Generate and edit images via the Gemini API with text prompts.

Updated Jun 4, 2026
One-click install
npx skills add https://github.com/hemory/amp --skill gemini-imagegen-hemory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/hemory/amp/tree/main/.claude/plugins/compound-engineering/skills/gemini-imagegen
Command: npx skills add https://github.com/hemory/amp --skill gemini-imagegen-hemory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, Pillow, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the creation and modification of images using the Gemini API, eliminating the need for complex graphic design software or manual editing for many common tasks.

Core Features & Use Cases

  • Text-to-Image Generation: Generate unique images from detailed text prompts.
  • Image Editing & Manipulation: Modify existing images by adding elements, changing styles, or applying effects.
  • Multi-Turn Refinement: Iteratively improve generated or edited images through conversational prompts.
  • Use Case: Generate a logo for a new startup by providing a description and then refine it by asking for specific color changes or font adjustments.

Quick Start

Use the gemini-imagegen skill to generate an image of a futuristic cityscape at sunset.

Frequently Asked Questions about gemini-imagegen

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

FAQPage Schema
How do I generate images from text using the Gemini API?

Text-to-image generation with the Gemini API involves sending descriptive text prompts to create unique visual content. This skill automates that process using the google-genai library to handle prompt processing and return generated images.

What do I need to set up to edit images with Gemini?

Editing images with Gemini requires setting the GEMINI_API_KEY environment variable. You also need the Pillow library for image processing and the google-genai dependency to handle the API interactions for modifying existing images.

Can I iteratively refine AI art after generating it?

Iterative refinement of AI art is supported through multi-turn conversational prompts. You can request specific adjustments like color changes or font updates to an initially generated image until the visual content meets your requirements.

What is the best way to create a logo without manual graphic design software?

Creating a logo without manual software is best done by providing a detailed text description to an AI image generator. This skill uses the Gemini API to generate the initial design and allows for iterative refinement through conversational prompts.

Does this text-to-image approach work for scene generation and artistic style transfer?

Text-to-image generation works for scene generation and artistic style transfer by interpreting detailed text prompts. The Gemini API processes these descriptions to generate new scenes or apply specific visual styles to existing images.

Why is my Gemini image generation not working?

Gemini image generation might not work if the GEMINI_API_KEY environment variable is missing or invalid. Ensure both google-genai and Pillow dependencies are correctly installed in your environment to avoid processing failures.