skills.rest
xdanger
xdangerCOMMUNITY
Explore all skills by this author →
Website𝕏@xdangerGitHub

nano-banana-pro

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

3|1|Updated Jun 14, 2021
Search Tags:#editing#api#image#ai#gemini#generate#resolution
One-click install
npx skills add https://github.com/xdanger/dotfiles --skill nano-banana-pro-xdanger
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/xdanger/dotfiles/tree/main/agents/skills/nano-banana-pro
Command: npx skills add https://github.com/xdanger/dotfiles --skill nano-banana-pro-xdanger

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai>=1.0.0, pillow>=10.0.0, and includes scripts (resource) components.

What problem does it solve?

This Skill enables automated image generation and editing using Gemini 3 Pro Image API, eliminating manual, repetitive image creation and modification workflows.

Core Features & Use Cases

  • Text-to-image generation from descriptive prompts with configurable resolutions (1K, 2K, 4K) and optional aspect ratios.
  • Image editing using an input image and editing prompts to modify visuals without starting from scratch.
  • End-to-end workflow: API key handling via --api-key or GEMINI_API_KEY and saving results to the user’s working directory.

Quick Start

Run the generate_image.py script with a prompt and an output filename to create a new image, optionally providing an input image and a desired resolution.

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 using the Gemini API?▼

To generate images from text using the Gemini API, provide a descriptive prompt and output filename to the generate_image.py script, which uses Gemini 3 Pro to create and save the visual to your working directory.

Can I edit an existing image with Gemini 3 Pro?▼

Yes, you can edit an existing image with Gemini 3 Pro by passing an input image file alongside your editing prompts, allowing you to modify visuals directly without starting from scratch.

Do I need an API key to use Gemini for image generation?▼

Yes, you need an API key to use Gemini for image generation, which must be provided either via the --api-key command line flag or by setting the GEMINI_API_KEY environment variable.

What resolutions and aspect ratios are supported for Gemini image generation?▼

Gemini image generation supports configurable resolutions of 1K, 2K, or 4K and allows you to specify optional aspect ratios to meet your specific output formatting requirements.

How do I automate repetitive image creation workflows with Python?▼

You can automate repetitive image creation workflows with Python by running the generate_image.py script with text prompts to programmatically generate or modify images using the Google Gemini API.

Are there limitations when modifying images with Gemini 3 Pro?▼

When modifying images with Gemini 3 Pro, you are limited to the capabilities of the Google Gemini API and must supply a valid input image alongside text prompts to achieve the desired visual edits.

Related Skills

Explore More Software Engineering Skills→
gvkhoslagvkhosla
49

gemini-imagegen

Generate and edit images via the Gemini API with text prompts.

Community
Intermediate
doanchienthangdevdoanchienthangdev
4

Processing Images

Optimize, resize, convert, and batch process images with the Sharp library.

Community
Intermediate
8b-is8b-is

gemini-imagegen

Generate and edit images via the Gemini API in Python.

Official
Advanced
nesihaver-ILnesihaver-IL

nano-banana-pro

Generate branded visuals with Gemini 3 Pro Image API using configurable aspect ratios and resolutions.

Community
Intermediate