skills.rest
steipete
steipeteCOMMUNITY
Explore all skills by this author →
Website𝕏@steipeteGitHub

nano-banana-pro

Generate or edit images via Gemini 3 Pro Image API with PNG output.

386k|81.1k|Updated Nov 24, 2025
Search Tags:#image generation#image editing#gemini#creative automation#ai art
One-click install
npx skills add https://github.com/steipete/clawdis --skill nano-banana-pro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/steipete/clawdis/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/steipete/clawdis --skill nano-banana-pro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires uv, GEMINI_API_KEY, and includes scripts (resource) components.

What problem does it solve?

This Skill automates image creation and editing using natural language instructions, eliminating the need for graphic design skills and manual editing tools.

Core Features & Use Cases

  • AI Image Generation: Create stunning visuals from text descriptions.
  • Use Case: When you need marketing visuals, concept art, or product images without hiring designers or learning complex software.

Quick Start

Generate an image of "a cyberpunk cityscape at night with neon lights" and save it as 'cyber-city.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 images from text prompts using AI?▼

Image generation from text prompts uses AI models to create visuals directly from natural language descriptions. This Skill generates images at 1K, 2K, or 4K resolution via the Gemini 3 Pro Image API by running a Python script that converts your prompt into a PNG file without requiring design software or manual editing.

Can I edit existing images with AI instead of using design software?▼

Yes, AI image editing modifies existing images using natural language instructions. This Skill accepts an optional input image and applies edits through the Gemini API, letting you adjust visuals without learning complex design tools—output saves as PNG.

What do I need to generate images with Gemini's API?▼

You need a Gemini API key (GEMINI_API_KEY) to authenticate requests, the uv package manager to run the generate_image.py script, and Python installed. You can pass the API key as an environment variable or via --api-key flag at runtime.

What image resolutions does AI image generation support?▼

This Skill supports generating images at 1K, 2K, and 4K resolutions through Gemini 3 Pro's image API. Resolution selection determines output file size and detail level when creating or editing visuals from prompts.

How do I start generating images without installing complex software?▼

Install uv, set your GEMINI_API_KEY environment variable, then run the generate_image.py script with a text prompt. The script handles API calls and outputs a PNG file path—no graphic design experience or software installation required.

Can I automate image creation for marketing or concept art?▼

Yes, this Skill automates image creation from text descriptions, eliminating manual design work for marketing visuals, concept art, and product images. Run it via script to generate PNG files at your chosen resolution without hiring designers or learning design software.

Related Skills

Explore More Design & Creative Skills→
spoonbobospoonbobo

nano-banana-pro

Generate and edit images with the Gemini 3 Pro Image model via Python.

Community
Intermediate
AcosmiAcosmi
6

image

Generate, edit, analyze, and convert images via configured vision models.

Community
Advanced
Syh1906Syh1906
25

openai-compatible-imagegen

Automates image generation, editing, and batch creation via OpenAI-compatible API with Python.

Community
Advanced
veniceaiveniceai
130

venice-image-edit

Modify and generate images via Venice's API using text prompts.

Official
Intermediate