nano-banana

Nano Banana creates images from text descriptions using three selectable models—pick the standard version for speed, pro for top quality, or legacy for compatibility. The skill also edits existing images and combines multiple images into compositions, with automatic compression for large inputs.

Nano Banana generates images from text prompts using three model options, from fast standard quality to highest-quality output.

AI-generated summary based on this skill's SKILL.md

★ 3,230 ⁮ 260 MIT updated 2026-04-26 by nexu-io

Install

nexu-io/nexu/nano-banana · repository language: TypeScript

Manual (git clone) CLI (skillfed)

git clone https://github.com/nexu-io/nexu
cp -r nexu/skills/nexubot/nano-banana ~/.claude/skills/nano-banana

npx skillfed install nexu-io/nexu/nano-banana

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I generate an image from text with nano-banana?

Nano Banana creates images from text descriptions using three selectable models. Provide your text prompt, choose between the standard version for speed, pro for top quality, or legacy for compatibility, and nano-banana will generate your image. The skill handles the AI image synthesis automatically.

Can nano-banana edit images with AI using text prompts?

Yes, nano-banana supports editing existing images using text instructions. Beyond generating new images from descriptions, you can modify and refine existing images by providing text prompts that describe your desired changes, making it a versatile AI image editor.

What's the difference between nano-banana's model options?

Nano Banana offers three models to match your needs: standard for fast generation, pro for the highest quality output, and legacy for compatibility with older workflows. Choose based on whether you prioritize speed or image quality for your specific project.

Can I create a collage or combine multiple images with nano-banana?

Nano Banana can create collages and composites from multiple input images. The skill automatically handles compression for large inputs, making it easy to combine several images into a single composition without manual resizing.

What resolutions and aspect ratios does nano-banana support?

Nano Banana generates images at specific resolutions and aspect ratios you specify. Whether you need standard dimensions or custom sizes like 4K quality, you can control the output format to match your requirements.

Is nano-banana free to use and what license does it have?

Nano Banana is released under the MIT license, making it free and open for use. The MIT license allows you to use, modify, and distribute the skill with minimal restrictions.

SKILL.md

rendered from the published skill — quoted content, verbatim

Nano Banana — Image Generation

Image generation script supporting three models. Requires sharp for input image compression (auto-installed on first run).

Models

Flag	Notes
`--model nano-banana`	Default. Fast, good quality.
`--model nano-banana-pro`	Highest quality, slower.
`--model nano-banana-2`	Legacy model.

Generate an image

node {baseDir}/scripts/generate-image.js --prompt "a cat sitting on mars" --filename "cat-on-mars.png"

Edit a single image

node {baseDir}/scripts/generate-image.js \
  --prompt "make the sky purple" \
  --filename "edited.png" \
  -i "/path/to/input.png" \
  --model nano-banana-pro

Multi-image composition (up to 14 images)

```bash node {baseDir}/scripts/generate-image.js \ --prompt "combine these into a collage"

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 3 files

skills/nexubot/nano-banana/SKILL.md
skills/nexubot/nano-banana/scripts/generate-image.js
skills/nexubot/nano-banana/scripts/package.json

All skills by nexu-io →