nanaban

Nano Banana 2 CLI — generate images from the terminal. 3 seconds, one command.

A CLI for Nano Banana 2 and Nano Banana Pro. One install, one command, one image. Works for humans typing prompts and AI agents calling --json.

npm install -g nanaban
nanaban "a fox in snow"

Auto-named, saved to your current directory, done. If you use OpenClaw, paste this repo URL and let it handle the rest.

What it looks like

nanaban "cyberpunk tokyo street neon rain" --ar wide

nanaban "minimalist single line fox"

nanaban "product photo white ceramic mug"

Every image on this page was generated with nanaban. ~3 seconds each, straight from the terminal.

Why nanaban

Most image generation tools make you open a browser, wait in a queue, click through UI, download manually. nanaban cuts all of that:

• One command — type your prompt, get a file. No browser, no signup flow, no queue.
• Auto-names files — "a fox in a snowy forest at dawn" becomes fox_snowy_forest_dawn.png. No more image_032_final_v2.png.
• Built for scripts — stdout is always the file path. nanaban "a cat" | xargs open just works.
• Built for LLM agents — --json gives you structured output. Plug it into any AI pipeline.
• Tiny — 6 dependencies. Ships TypeScript source directly, no build step.

Install

npm install -g nanaban

Needs Node 18+. That's the only requirement.

Want to work from source instead?

git clone https://github.com/199-biotechnologies/nanaban.git
cd nanaban && npm install && npm link

Setup (30 seconds)

You need a Google Gemini API key. It's free and takes a minute:

1. Go to Google AI Studio
2. Sign in with any Google account
3. Click Create API Key
4. Pick any Google Cloud project (or let it create one for you)
5. Copy the key — it starts with AIzaSy...

Then store it once:

nanaban auth set AIzaSy...

That's it. The key persists across sessions. You can also set GEMINI_API_KEY or GOOGLE_API_KEY as an environment variable if you prefer.

Check what's configured anytime:

nanaban auth

Usage

nanaban "prompt"                          # auto-names, saves to CWD
nanaban "prompt" -o sunset.png            # pick your own filename
nanaban "prompt" --ar wide --size 2k      # 16:9, high resolution
nanaban "prompt" --pro                    # higher quality model
nanaban "prompt" --neg "blurry, text"     # negative prompt
nanaban "prompt" -r style.png            # match the style of another image
nanaban edit photo.png "add sunglasses"   # edit an existing image

Flags

Every flag works with both nanaban "prompt" and nanaban edit.

Aspect Ratios

14 aspect ratios — from square to extreme panoramic:

Note: 1:4, 4:1, 1:8, 8:1 are only available on the NB2 (default) model. Pro supports the standard 10 ratios.

Reference images

Pass any image as a style or content reference with -r:

nanaban "portrait of a woman" -r painting_style.png
nanaban "modern living room" -r color_palette.jpg
nanaban "product shot" -r brand_reference.png

The model picks up on the visual language of your reference — color palette, composition, texture, artistic style — and applies it to your prompt. Useful for keeping a consistent look across a batch of images, matching brand aesthetics, or steering the output toward a specific vibe without writing a 200-word prompt.

Editing existing images

nanaban edit photo.png "remove the background"
nanaban edit headshot.png "make it a pencil sketch"
nanaban edit product.png "place on a marble table" --ar wide

Takes a source image and your edit instruction. Same flags apply — you can change aspect ratio, resolution, use Pro for finer edits.

Models

Both run on Gemini's image generation models (gemini-3.1-flash-image-preview and gemini-3-pro-image-preview).

For LLM agents and scripts

--json gives you machine-readable output. No spinners, no colors, no ambiguity:

nanaban "a red circle" --json

{
  "status": "success",
  "file": "/Users/you/red_circle.png",
  "model": "gemini-3.1-flash-image-preview",
  "dimensions": { "width": 1024, "height": 1024 },
  "size_bytes": 1247283,
  "duration_ms": 12400
}

Errors come back in the same shape:

{
  "status": "error",
  "code": "AUTH_MISSING",
  "message": "No authentication found."
}

Error codes: AUTH_MISSING, AUTH_INVALID, AUTH_EXPIRED, PROMPT_MISSING, IMAGE_NOT_FOUND, GENERATION_FAILED, RATE_LIMITED, NETWORK_ERROR.

Exit codes: 0 success, 1 runtime error, 2 usage error.

Piping

stdout is always just the file path. Metadata goes to stderr. So these compose naturally:

nanaban "a cat" | xargs open                              # generate and open
nanaban "a cat" 2>/dev/null | pbcopy                       # copy path to clipboard
cat prompts.txt | while read p; do nanaban "$p"; done      # batch generate

Auto-naming

Your prompt becomes the filename. Common words get stripped, capped at 6 words, joined with underscores:

"a fox in a snowy forest at dawn" → fox_snowy_forest_dawn.png

Collisions auto-increment: fox_snowy_forest.png, fox_snowy_forest_2.png, fox_snowy_forest_3.png.

Dependencies

Deliberately small:

• @google/genai + google-auth-library — Gemini API access
• commander — CLI parsing (~90KB)
• nanospinner — terminal spinner (~3KB)
• picocolors — terminal colors (~3KB)
• tsx + typescript — runs TypeScript source directly, no build step

License

ISC

Author

Boris Djordjevic