gemini-imagegen

SKILL.md

Text-to-image and image editing using Google's Gemini API with multi-turn refinement support.

Supports text-to-image generation, image editing, style transfer, and composition from up to 14 reference images

Configurable resolution (1K, 2K, 4K) and 10 aspect ratios including square, landscape, portrait, and panoramic formats

Multi-turn chat interface for iterative refinement and editing workflows

Google Search grounding for generating images based on real-time data

Requires GEMINI_API_KEY environment variable; returns JPEG format by default

Gemini Image Generation (Nano Banana Pro)

Generate and edit images using Google's Gemini API. The environment variable GEMINI_API_KEY must be set.

Default Model

Model
Resolution
Best For

gemini-3-pro-image-preview
1K-4K
All image generation (default)

Note: Always use this Pro model. Only use a different model if explicitly requested.

Quick Reference

Default Settings

Model: gemini-3-pro-image-preview

Resolution: 1K (default, options: 1K, 2K, 4K)

Aspect Ratio: 1:1 (default)