mcpField
N
nano-banana

nano-banana

github.com/inference-shCreative & media790982 installsUpdated 2w ago
Repository

About nano-banana

nano-banana is a belt CLI skill for generating and editing images with Google Gemini image models. It is for users who want to invoke the models from the command line and configure image count, aspect ratio, resolution, or search grounding.

Key features

  1. 01Text-to-image generation
  2. 02Editing with input images
  3. 03Multiple image outputs
  4. 04Aspect ratio and resolution options
  5. 05Google Search grounding option

Use cases

  1. 01Creating images from text prompts
  2. 02Editing an existing image with a prompt
  3. 03Generating several logo concepts
  4. 04Producing a high-resolution image

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/inference-sh/skills --skill nano-banana

After installing, type/nano-bananain Claude Code to confirm it loaded.

Details

From the project README

Install the belt CLI skill: npx skills add belt-sh/cli

Nano Banana - Gemini Native Image Generation

Generate images with Google Gemini native image models via inference.sh CLI.

Nano Banana

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

belt app run google/gemini-3-pro-image --input '{"prompt": "a banana in space, photorealistic"}'

Models

ModelApp IDSpeedQuality
Gemini 3 Pro Imagegoogle/gemini-3-pro-imageSlowerBest
Gemini 2.5 Flash Imagegoogle/gemini-2-5-flash-imageFastExcellent

Search Gemini Image Apps

belt app search "gemini image"

Examples

Basic Text-to-Image
belt app run google/gemini-3-pro-image --input '{
  "prompt": "A futuristic cityscape at sunset with flying cars"
}'
Multiple Images
belt app run google/gemini-2-5-flash-image --input '{
  "prompt": "Minimalist logo design for a coffee shop",
  "num_images": 4
}'
Custom Aspect Ratio
belt app run google/gemini-3-pro-image --input '{
  "prompt": "Panoramic mountain landscape with northern lights",
  "aspect_ratio": "16:9"
}'
Image Editing (with input image)
belt app run google/gemini-2-5-flash-image --input '{
  "prompt": "Add a rainbow in the sky",
  "images": ["https://example.com/landscape.jpg"]
}'
High Resolution (4K)
belt app run google/gemini-3-pro-image --input '{
  "prompt": "Detailed illustration of a medieval castle",
  "resolution": "4K"
}'
With Google Search Grounding
belt app run google/gemini-3-pro-image --input '{
  "prompt": "Current weather in Tokyo visualized as an artistic scene",
  "enable_google_search": true
}'

Input Options

ParameterTypeDescription
promptstringRequired. What to generate or change
imagesarrayInput images for editing (up to 14)
num_imagesintegerNumber of images to generate
aspect_ratiostringOutput ratio: "1:1", "16:9", "9:16", "4:3", "3:4", "auto"
resolutionstring"1K", "2K", "4K" (Gemini 3 Pro only)
output_formatstringOutput format for images
enable_google_searchbooleanEnable real-time info grounding

Prompt Tips

Styles: photorealistic, illustration, watercolor, oil painting, digital art, anime, 3D render

Composition: close-up, wide shot, aerial view, macro, portrait, landscape

Lighting: natural light, studio lighting, golden hour, dramatic shadows, neon

Details: add specific details about textures, colors, mood, atmosphere

Sample Workflow

# 1. Generate sample input to see all options
belt app sample google/gemini-3-pro-image --save input.json

# 2. Edit the prompt
# 3. Run
belt app run google/gemini-3-pro-image --input input.json

Related Skills

# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli

# All image generation models
npx skills add inference-sh/skills@ai-image-generation

# Video generation (for image-to-video)
npx skills add inference-sh/skills@ai-video-generation

Browse all image apps: belt app list --category image

Documentation

Comments

Markdown supported