gemini-imagegen

Generate and edit images via the Gemini API with configurable aspect ratio.

Updated Aug 23, 2026

Search Tags:#image #AI #composition #Gemini #generate #image-editing #reference-images

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables rapid creation and editing of images using the Gemini API, removing the need for manual graphic workflows and enabling on-demand visuals from textual prompts.

Core Features & Use Cases

Text-to-image generation from prompts with adjustable aspect ratio and resolution.
Edit existing images by applying textual edits or style changes, using optional reference inputs.
Compose multiple reference images (up to 14) into a single scene.
Engage in multi-turn refinement chats to iteratively improve outputs.
Suitable for design, marketing, product mockups, and rapid prototyping.

Quick Start

Use the gemini-imagegen skill to generate an image from the prompt "A futuristic city skyline at sunset" and save it as output.png.

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 prompts using the Gemini API?▼

You provide a textual description and configure aspect ratio and image size to generate images from text prompts using the Gemini API.

Can I use reference images to compose a single scene with Gemini AI?▼

Yes, you can use reference images to compose a single scene with Gemini AI. The Skill supports combining up to 14 reference images into one visual composition.

What do I need to set up before editing images with the Gemini API?▼

Before editing images with the Gemini API, you need to set the GEMINI_API_KEY environment variable and ensure the Pillow and google-genai dependencies are installed in your environment.

How do I edit existing images by applying style changes with Gemini?▼

To edit existing images with Gemini, you pass the target image and apply textual edits or style changes to modify the visual content, optionally using reference inputs for guidance.

Does Gemini image generation support iterative refinement for design mockups?▼

Yes, Gemini image generation supports iterative refinement for design mockups. You can engage in multi-turn refinement chats to gradually improve and adjust your visual outputs.

Can I enhance text-to-image generation results using Google Search grounding?▼

Yes, you can enhance text-to-image generation results using optional Google Search grounding to provide additional context and improve the accuracy of the generated visuals.