Index of every page on this site: llms.txt
All skills
inference-sh avatar

/nano-banana

@c895a47
by inference.shinference-sh/skills819 stars
108
Run it yourself

Generate images with Google Gemini native image models via inference.sh CLI. Models: Gemini 3 Pro Image (Nano Banana Pro), Nano Banana 2.1. Capabilities: text-to-image, image editing, multi-image input. Triggers: nano banana, gemini image, gemini 3 pro image, nano banana pro, nano banana 2.1, google image generation, native image generation, gemini native image

Use this Skill: https://skilld.dev/gh/inference-sh/skills/nano-banana

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈94 tokens for metadata: the name and description. ≈933 when used: this file.

Description uses 4.7% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈377 characters, or 4.7%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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

Model App ID Speed Quality
Gemini 3 Pro Image google/gemini-3-pro-image Slower Best
Nano Banana 2.1 google/gemini-nano-banana-2-1 Fast Excellent

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-nano-banana-2-1 --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-nano-banana-2-1 --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

Parameter Type Description
prompt string Required. What to generate or change
images array Input images for editing (up to 14)
num_images integer Number of images to generate
aspect_ratio string Output ratio: "1:1", "16:9", "9:16", "4:3", "3:4", "auto"
resolution string "1K", "2K", "4K"
output_format string Output format for images
enable_google_search boolean Enable 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

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alert3d5 checks · Risk SAFE
  • Gen Agent Trust Hub3d

    The skill provides instructions for using the inference.sh CLI to generate images with Google Gemini models. It utilizes the vendor's official CLI tool and documentation to facilitate image generation tasks.

  • Socket3d

    No alerts

  • Snyk3d

    Risk: CRITICAL · 3 issues

  • Runlayer8mo

    1/1 file flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at c895a47. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 4 days ago
What it can do
Runs commands
All 1 allowed tools
Bash(belt *)
  • CLI
  • gemini
  • image-generation
  • text-to-image
  • image-editing
  • google
  • inference-sh
  • belt
  • ai-image

README badge

README badge for inference-sh/skills/nano-banana

Generates images with Google Gemini native image models (Gemini 3 Pro Image and Gemini 2.5 Flash Image) via the inference.sh CLI. Supports text-to-image, image editing with input images, custom aspect ratios, and real-time Google Search grounding.

Generated from the current SKILL.md.

What image models does this skill support?
Gemini 3 Pro Image (best quality, slower) and Gemini 2.5 Flash Image (fast, excellent quality). Both support text-to-image, image editing, and multi-image generation.
Do I need to install anything separately?
Yes. The skill requires the inference.sh CLI (belt) and a Google API key. Install instructions are provided in the skill documentation.
Can I edit existing images or only generate from text?
Both. You can generate from text prompts or edit existing images by passing image URLs in the input, up to 14 images at once.
What output resolutions are available?
Gemini 3 Pro Image supports 1K, 2K, and 4K resolutions. Gemini 2.5 Flash Image does not have a resolution parameter.
Does this support custom aspect ratios?
Yes. You can specify aspect ratios like 1:1, 16:9, 9:16, 4:3, 3:4, or auto.

Generated from the current SKILL.md. These answers refresh after source changes.