gemini-imagegen

Generate and edit images from natural language prompts via the Gemini API.

1|Updated Dec 29, 2025

Search Tags:#image generation #composition #image editing #Gemini API #generate #multi-turn

Ready to run

npx skills add https://github.com/nunomen/claude-skills --skill gemini-imagegen-nunomen

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/nunomen/claude-skills/tree/main/gemini-imagegen
Command: npx skills add https://github.com/nunomen/claude-skills --skill gemini-imagegen-nunomen

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables rapid creation and editing of images by leveraging the Gemini API, removing tedious manual design work and accelerating visual iterations.

Core Features & Use Cases

Generate images from natural language prompts using Gemini API.
Edit existing images with textual instructions and optional aspect ratios and resolutions.
Compose multiple reference images into a single scene for logos, stickers, or product mockups.
Use multi-turn chat for iterative refinement of visuals.

Quick Start

Use the gemini-imagegen skill to generate an image from a prompt, e.g., "A sunset over mountains" and save as "sunset.jpg".

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 natural language prompts using the Gemini API?▼

You generate images from natural language prompts by automating the Gemini API to process text instructions and produce corresponding visuals. This removes manual design work and accelerates visual iterations.

Can I edit existing images and compose multiple reference images with Gemini API?▼

You can edit existing images using textual instructions and compose multiple reference images into a single unified visual. This supports creating product mockups, logos, and stickers.

How does multi-turn chat refine image generation and editing workflows?▼

Multi-turn chat refines image generation by allowing iterative visual adjustments based on sequential textual instructions. This enables progressive enhancement of generated images across conversational turns.

Do I need Python and specific dependencies to use the Gemini API for image generation?▼

You need Python 3.11+ along with the google-genai and Pillow dependencies. You must also set the GEMINI_API_KEY environment variable for authentication before generating or editing images.

What are the limitations of using natural language prompts for image editing?▼

Limitations of natural language image editing include dependency on prompt clarity and the Gemini API's interpretation accuracy. Complex compositions may require multi-turn iterative refinement to achieve desired visual outputs.