skills.rest
prateek
prateekCOMMUNITY
Explore all skills by this author →
GitHub

image-gen-nano-banana

Generate or edit images locally via Gemini with Flash or Pro models.

3|Updated Jan 14, 2014
Search Tags:#workflow#gemini#image-generation#ai-art#prompt-writing#local-skill
One-click install
npx skills add https://github.com/prateek/dotfiles --skill image-gen-nano-banana
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-gen-nano-banana
Source: https://github.com/prateek/dotfiles/tree/main/.agents/skills/image-gen-nano-banana
Command: npx skills add https://github.com/prateek/dotfiles --skill image-gen-nano-banana

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai>=1.65.0, pillow>=12.1.1, and includes scripts (resource) components.

What problem does it solve?

Enables local, self-contained image generation and editing using Gemini via a Nano Banana path, keeping prompt authoring guidance instructional and separate from the execution engine.

Core Features & Use Cases

  • Directly generate or edit images with Flash or Pro models through a locally owned workflow.
  • Use Kousen-style prompt rewriting in conversation to craft precise prompts, while the runner executes the generation verbatim.
  • Manage outputs and references with an explicit, predictable workflow suitable for production-ready prompts and assets.

Quick Start

Provide a natural-language prompt and let the skill guide you through on-demand prompt refinement before running the generator.

Frequently Asked Questions about image-gen-nano-banana

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

FAQPage Schema
How do I generate images locally using Gemini?▼

The skill enables local image generation with Gemini by separating prompt authoring from the execution engine, managing outputs and references with an explicit, predictable workflow for reproducible results.

Can I edit existing images with Gemini Flash or Pro models?▼

Yes, you can edit existing images directly with Gemini Flash or Pro models through the local Nano Banana path, managing references and outputs with an explicit, predictable workflow for reproducible results.

Do I need the google-genai package to run local image generation?▼

The environment requires google-genai and pillow dependencies to support frontmatter-driven configuration and output management for generating images with Gemini.

What is the best way to write prompts for AI image generation?▼

Interactive prompt refinement helps you craft precise, production-ready prompts for diverse styles, scales, and references before committing the generation request to the Gemini models.

How do I ensure reproducible results when generating AI art?▼

You ensure reproducible AI art results by using frontmatter-driven configuration and explicit output and reference management, keeping prompt authoring separate from the execution engine for predictable workflow behavior.

When should I use the Pro model instead of Flash for image generation?▼

You should choose between Flash and Pro models based on your need for diverse styles, scales, and references, applying frontmatter-driven configuration to satisfy specific production-ready prompt requirements.

Related Skills

Explore More Design & Creative Skills→
abhiunixabhiunix
1

nano-banana-pro

Generate or edit images with Gemini 3 Pro Image via a local script.

Community
Intermediate
SJTU-IPADSSJTU-IPADS
7

image-utils

Automate deterministic image editing tasks on image collections with Pillow.

Official
Intermediate
kienhaminhkienhaminh

gemini-image-gen

Generate and edit images from text prompts using Gemini 2.5 Flash Image.

Community
Advanced
fcouryfcoury
1

nano-banana-builder

Create full-stack web apps using Google Gemini Nano Banana image APIs.

Community
Advanced