se-gemini-imagegen

Generate and edit images using the Gemini API.

Updated May 7, 2026

Search Tags:#image #composition #gemini #edit #generate #reference-images #ai-art

Ready to run

npx skills add https://github.com/simonwjackson/pi-software-engineering --skill se-gemini-imagegen

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: se-gemini-imagegen
Source: https://github.com/simonwjackson/pi-software-engineering/tree/main/skills/se-gemini-imagegen
Command: npx skills add https://github.com/simonwjackson/pi-software-engineering --skill se-gemini-imagegen

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Gemini image generation and editing tasks are time-consuming and require multiple tools; this skill provides a unified interface to generate and refine visuals using the Gemini API.

Core Features & Use Cases

Text-to-Image Generation: Create images from prompts with configurable aspect ratios and resolutions.
Image Editing & Style Transfer: Modify existing images or apply styles based on natural language instructions.
Multi-turn Refinement & Composition: Iterate prompts and combine multiple reference images to build complex scenes.

Quick Start

Generate an image from the prompt "A futuristic city skyline" using Gemini API.

Frequently Asked Questions about se-gemini-imagegen

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

FAQPage Schema

How do I generate images using the Gemini API from text prompts?▼

To generate images using the Gemini API, you provide a text prompt to automate text-to-image generation. This skill uses the Google Gemini GenAI library to create visuals with configurable aspect ratios and resolutions from your descriptions.

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 using natural language instructions. This allows you to modify visuals or apply new styles to images directly through the Gemini API.

How many reference images can I use for multi-turn image composition?▼

You can use up to 14 reference images for multi-turn image composition. This allows you to combine multiple visuals and iterate on prompts to build complex scenes and refine generated images.

Do I need a specific API key to use the Gemini API for image generation?▼

Yes, you need a GEMINI_API_KEY to authenticate and use the Gemini API for image generation. You must configure this key in your environment to automate creative tasks and generate visuals.

What image processing dependencies are required to automate Gemini image generation?▼

Automating Gemini image generation requires the google-genai library for API interaction and Pillow for image processing. These dependencies support handling both TEXT and IMAGE modalities for generation and editing.

What are the limitations of using Gemini AI for text-to-image generation?▼

Gemini AI text-to-image generation is limited to processing up to 14 reference images for composition and requires a valid GEMINI_API_KEY. It supports TEXT and IMAGE modalities to automate creative tasks within these constraints.