gemini-imagegen

Generate and edit images via the Gemini API with configurable settings.

102|4|Updated Apr 15, 2009

Search Tags:#images #composition #generate #prompt #image-editing #ai-art #gemini-api

Ready to run

npx skills add https://github.com/mikker/dotfiles --skill gemini-imagegen-mikker

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill provides a robust interface to generate and edit images using the Gemini API, enabling quick visual content creation from textual prompts and iterative refinements.

Core Features & Use Cases

Generate high-quality images from text prompts using Gemini's pro and standard models with configurable aspect ratios and resolutions.
Edit existing images by applying instructions, allowing multi-turn refinements and style adjustments.
Compose or combine multiple inputs into a final image and perform guided iterations or interactive chats for design exploration.

Quick Start

Generate a 1024x1024 image of a futuristic city 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 prompts using the Gemini API?▼

You can generate images from text prompts using the Gemini API by providing a textual description and configuring parameters like aspect ratio and image size. The skill uses the Google Gemini Python client to call generate_content, returning the generated visual output and an optional textual response.

Can I edit existing images and apply style transfers with Gemini AI?▼

Yes, you can edit existing images and apply style transfers with Gemini AI by submitting reference images alongside text instructions. This workflow supports multi-turn refinements, style adjustments, and multi-image compositions for interactive design exploration.

Do I need a GEMINI_API_KEY to automate visual content creation?▼

Yes, you need a GEMINI_API_KEY to automate visual content creation because the skill relies on the Google Gemini Python client to authenticate requests. It uses this key to call generate_content for text-to-image generation and image editing workflows.

What is the best way to compose multiple inputs into a final image?▼

The best way to compose multiple inputs into a final image is by providing multiple reference images to the Gemini API. The skill processes these inputs with configurable image_config settings to merge visuals, overlay logos, or create product mockups in a single output.

Does image generation with the Gemini API work with Pillow?▼

Image generation with the Gemini API works alongside Pillow as a dependency for handling the returned image data. While the Google Gemini client generates the visual content, Pillow manages local image processing tasks within your Python scripts.