Back to Skills

nano-banana

Generate images with Google Gemini native image models via inference.sh CLI. Models: Gemini 3 Pro Image, Gemini 2.5 Flash Image. Capabilities: text-to-image, image editing, multi-image input. Triggers: nano banana, gemini image, gemini 3 pro image, gemini 2.5 flash image, google image generation, native image generation, gemini native image

314stars49forksUpdated 4/8/2026

Security Assessment

Safe(100/100)
Security Score100/100

About nano-banana

The 'nano-banana' skill enables users to generate images using Google Gemini's native image models via the inference.sh CLI. This skill provides a streamlined method for generating and editing images by leveraging Gemini 3 Pro and Gemini 2.5 Flash Image models. It allows users to create photorealistic and artistic images based on textual descriptions, perform image editing with existing images, and generate multiple images with one command. This skill effectively simplifies the process of image generation and editing, making it accessible for users who need creative visual content without needing specialized design software.

FAQ

What models are available in the nano-banana skill?

The skill supports two models: Gemini 3 Pro Image and Gemini 2.5 Flash Image. Gemini 3 Pro offers the best quality but is slower, while Gemini 2.5 Flash is faster and provides excellent quality.

Can I generate multiple images at once?

Yes, you can generate multiple images by specifying the 'num_images' parameter when running the Gemini 2.5 Flash Image model.

What input options are available for customizing image generation?

Input options include 'prompt' (required), 'images' (for image editing), 'num_images' (to specify the number of images), 'aspect_ratio' (to customize the output ratio), 'resolution' (for high-resolution images), and 'enable_google_search' (for real-time information grounding).

Is there a specific command for high-resolution image generation?

Yes, you can specify the 'resolution' parameter as '1K', '2K', or '4K' when using the Gemini 3 Pro model to generate high-resolution images.

Do I need to install any additional tools to use this skill?

Yes, the skill requires the installation of the inference.sh CLI tool ('infsh'). You can find the installation instructions [here](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md).

Install nano-banana

Download and extract the skill files to your .claude/skills/ directory.

Quick Setup:

  1. Copy the skill folder to .claude/skills/
  2. Claude will automatically detect and use the skill