skills.rest
shalevamin
shalevaminCOMMUNITY
Explore all skills by this author →
GitHub

nano-banana-pro

Generate and edit images via the Gemini 3 Pro Image API.

Updated Mar 7, 2026
Search Tags:#png#image generation#image editing#gemini#text-to-image#google genai#multi-image composition
One-click install
npx skills add https://github.com/shalevamin/Tau_agent --skill nano-banana-pro-shalevamin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/shalevamin/Tau_agent/tree/main/tau-agent-main/skills/nano-banana-pro
Command: npx skills add https://github.com/shalevamin/Tau_agent --skill nano-banana-pro-shalevamin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, pillow, and includes scripts (resource) components.

What problem does it solve? Creating or editing images programmatically requires wiring up API clients, handling image encoding, and managing output files. This Skill wraps Google's Gemini 3 Pro Image (Nano Banana Pro) API in a single script so you can generate or edit images with one command. ## Core Features & Use Cases - Text-to-Image Generation: Create images from text prompts at 1K, 2K, or 4K resolution with optional aspect ratio control (1:1 through 21:9). - Image Editing & Composition: Edit a single image or combine up to 14 input images into one scene, with automatic resolution detection based on input dimensions. - Use Case: Ask the agent to generate a 9:16 portrait avatar, or pass three product photos and have them composited into a single marketing scene saved as a timestamped PNG. ## Quick Start Generate an image of a sunset over mountains at 2K resolution and save it as sunset.png.

Frequently Asked Questions about nano-banana-pro

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an image with the Gemini API from Python?▼

Run the bundled script with uv, passing a prompt and output filename: uv run generate_image.py --prompt "your description" --filename output.png. The script uses the google-genai client with the gemini-3-pro-image-preview model and saves the result as a PNG.

How do I edit or combine multiple images with Gemini 3 Pro Image?▼

Pass input images with repeated -i flags along with an edit prompt, for example -i img1.png -i img2.png. The API supports up to 14 input images, and the script auto-detects output resolution from the largest input dimension.

What resolutions and aspect ratios does Gemini 3 Pro Image support?▼

Resolutions are 1K, 2K, and 4K, with 1K as the default. Supported aspect ratios are 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9; without a flag the model chooses freely.

Why does the image generation script fail with an API key error?▼

The script exits if no Gemini API key is found. Provide it via the --api-key argument or set the GEMINI_API_KEY environment variable before running the command.

What are the limitations of multi-image composition with Nano Banana Pro?▼

Composition is capped at 14 input images per request, and exceeding that limit causes the script to exit with an error. All inputs must be readable image files loadable by Pillow.

Related Skills

Explore More Design & Creative Skills→
capaas2capaas2

image-fetcher

Fetch visual assets via web search, Playwright screenshots, and user files.

Community
Intermediate
danmaraudadanmarauda

Convex Agents Files

Automate file uploads, attachments, and media handling in Convex agent conversations.

Community
Intermediate
reason-machinesreason-machines
4

ai-pixel-perfect-design-generator

Generates visual design assets from text prompts via the AiPixelPerfect API.

Official
Intermediate
hongmaple0820hongmaple0820
9

openai-image-gen

Generate images from text prompts via the OpenAI Images API and save a gallery.

Community
Intermediate