skills.rest
LichAmnesia
LichAmnesiaCOMMUNITY
Explore all skills by this author →
Website𝕏@ShenHuangGitHub

nano-banana

Generate and edit images with Nano Banana 2 via Gemini API.

231|24|Updated Apr 11, 2026
Search Tags:#image-generation#image-editing#ai-model#visual-content#png-output#gemini-3.1
One-click install
npx skills add https://github.com/LichAmnesia/lich-skills --skill nano-banana-lichamnesia
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana
Source: https://github.com/LichAmnesia/lich-skills/tree/main/skills/nano-banana
Command: npx skills add https://github.com/LichAmnesia/lich-skills --skill nano-banana-lichamnesia

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?

Generate and edit images using Nano Banana 2.

Core Features & Use Cases

  • Text-to-image generation with a fast, cost-effective Gemini 3.1 model.
  • Image editing (background changes, object removal, style swaps) with input images.
  • Use Case: Create blog thumbnails, cover art, posters, or visuals for demos.

Quick Start

Prompt the AI with a description and a filename to generate an image, or supply an input image plus an edit instruction to modify it.

Frequently Asked Questions about nano-banana

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

FAQPage Schema
How do I generate images from text prompts for blog thumbnails?▼

Generate images from text prompts by providing a description and filename to the AI. It outputs PNG files suitable for blog thumbnails, using the Gemini 3.1 model with safe defaults.

Can I edit existing images by removing backgrounds or swapping styles?▼

Edit existing images by supplying an input image along with an instruction. The image editing supports background changes, object removal, and style swaps, outputting modified PNG files.

What resolutions are supported for AI image generation?▼

AI image generation supports 512, 1K, 2K, and 4K resolutions. The mechanism applies resolution inference and safe defaults to output PNG files based on your prompt.

Do I need a Gemini API key to generate and edit images?▼

Yes, an API key is required to generate and edit images. The tool relies on the Gemini 3.1 model to process text prompts and input images for visual content creation.

What is the best way to create 4K visual content for posters?▼

Create 4K visual content for posters by prompting the AI with a descriptive text and filename. It uses a fast, cost-effective Gemini 3.1 model to generate high-resolution PNG output.

Are there limitations when using the Gemini model for image editing?▼

Limitations include requiring a Gemini API key and accepting only PNG outputs. While it handles background changes and style swaps, users must provide explicit prompts and optional input images.

Related Skills

Explore More Design & Creative Skills→
TugoukezhangTugoukezhang
8

nano-banana-pro

Generate and edit images via Gemini 3 Pro Image API at 1K/2K/4K resolutions.

Community
Intermediate
wanrengangwanrengang
6

canvas-design

Generate custom visual art and static design artifacts in PNG and PDF formats.

Community
Advanced
Umbral-BotUmbral-Bot

pillow-imaging

Automate image processing tasks with Pillow for batch resizing and watermarking.

Official
Intermediate
jordanhubbardjordanhubbard
9

baoyu-comic

Generate knowledge comics from text with specified art styles and tones.

Community
Advanced