gemini-imagegen

Generate and edit images using the Gemini API.

2|Updated Feb 9, 2026

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

Ready to run

npx skills add https://github.com/SiTaggart/.agents --skill gemini-imagegen-sitaggart

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Gemini-imagegen enables generating and editing images using the Gemini API, enabling designers and developers to create visuals, iterate on concepts, and apply style transfers without manual drawing.

Core Features & Use Cases

Text-to-image generation and image editing with Gemini AI
Image composition from multiple references for mockups and concepts
Multi-turn refinement and interactive prompts for iterative results
Logo, sticker, and product mockup generation

Quick Start

Prompt the model with a description to generate an image and save the resulting file.

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 using the Gemini API and Python?▼

To generate images using the Gemini API, you provide a text prompt to the model and save the resulting file. This requires setting the GEMINI_API_KEY and installing the google-genai and Pillow libraries.

Can I combine multiple reference images for composition with AI?▼

Yes, you can combine multiple reference images for image composition. This allows you to create mockups and concepts by integrating visual elements from several sources into a single output.

How do I edit existing images and apply style transfers without manual drawing?▼

You can edit existing images and apply style transfers without manual drawing by using interactive prompts. The model supports multi-turn refinement to iteratively adjust and enhance your visuals.

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

Yes, you need a GEMINI_API_KEY to execute text-to-image generation and editing tasks. You must also install the Pillow and google-genai Python libraries to process and save the generated assets.

What is the best way to iterate on product mockups and sticker designs?▼

The best way to iterate on product mockups and sticker designs is using multi-turn refinement. You can generate initial concepts and progressively refine them through interactive prompts until you achieve the desired result.