skills.rest
JoeyJoziah
JoeyJoziahCOMMUNITY
Explore all skills by this author →
GitHub

nano-banana-pro

Generate and edit images from natural-language prompts using Gemini 3 Pro Image.

Updated Aug 13, 2025
Search Tags:#image generation#visual content#prompt design#image editing#gemini#ai graphics
One-click install
npx skills add https://github.com/JoeyJoziah/investment-analysis-platform --skill nano-banana-pro-joeyjoziah
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/JoeyJoziah/investment-analysis-platform/tree/main/.claude/skills/nano-banana-pro
Command: npx skills add https://github.com/JoeyJoziah/investment-analysis-platform --skill nano-banana-pro-joeyjoziah

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of creating or editing images by turning a short prompt into a ready-to-use visual through Gemini 3 Pro Image.

Core Features & Use Cases

  • Text-to-Image Generation: Produce original images from natural-language descriptions.
  • Image Editing: Refine, restyle, or modify an existing image using an input file and instructions.
  • Resolution Control: Choose 1K, 2K, or 4K outputs for different quality needs.
  • Use Case: Create marketing concepts, illustrations, social graphics, or rapid design iterations without opening a separate design tool.

Quick Start

Ask the skill to generate or edit an image for your project, specifying the desired look and output 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 prompts using Gemini?▼

Image generation from text prompts using Gemini works by submitting natural-language descriptions to the Gemini 3 Pro Image model, which processes the prompt and outputs a ready-to-use visual. You can specify desired looks and output resolutions directly in your request.

Can I edit existing images with AI without manual graphic work?▼

Editing existing images with AI without manual graphic work is possible by uploading an input file and providing natural-language instructions to refine or restyle the image. The Gemini 3 Pro Image model processes the input file and applies the requested modifications automatically.

Do I need a GEMINI_API_KEY to generate AI graphics?▼

A valid GEMINI_API_KEY is required to generate AI graphics, as the Skill relies on Gemini 3 Pro Image access for its core text-to-image generation and image editing capabilities. You must configure this key in your environment before running the script.

What output resolutions are supported for prompt-driven image generation?▼

Output resolutions supported for prompt-driven image generation include 1K, 2K, and 4K options. You can select the appropriate resolution based on your specific quality needs for marketing concepts, mockups, or social graphics.

What are the limitations of using Gemini for image editing?▼

Limitations of using Gemini for image editing include the strict requirement for Gemini 3 Pro Image access and a valid GEMINI_API_KEY. Iterative image refinement from uploaded inputs depends entirely on prompt-driven instructions rather than manual graphic design adjustments.

Related Skills

Explore More Design & Creative Skills→
davekilleendavekilleen
461

gemini-imagegen

Generate and edit images using Google's Gemini API.

Community
Intermediate
LigphiDonkLigphiDonk
708

inno-figure-gen

Automates text-to-image and image-to-image generation using Gemini 3 Pro.

Community
Intermediate
binan-makerbinan-maker

photo-editor

Resize, crop, filter, and optimize images with Pillow and OpenCV.

Community
Advanced
happycapy-aihappycapy-ai
137

ai-image-generation

Generate AI images via text-to-image, image-to-image, and inpainting using the inference.sh CLI.

Community
Intermediate