skills.rest
Benmore-Studio
Benmore-StudioOFFICIAL
Explore all skills by this author →
WebsiteGitHub

nano_banana

Generate and edit images via the Gemini 2.5 flash-image model.

1|Updated Jan 28, 2026
Search Tags:#image-generation#api-integration#image-editing#prompt-based#gemini-2.5#base64-decoding
One-click install
npx skills add https://github.com/Benmore-Studio/Benmore-Meridian --skill nano-banana-benmore-studio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano_banana
Source: https://github.com/Benmore-Studio/Benmore-Meridian/tree/main/skills/nano_banana
Command: npx skills add https://github.com/Benmore-Studio/Benmore-Meridian --skill nano-banana-benmore-studio

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This tool enables rapid creation or modification of visuals by interfacing with the Gemini 2.5 flash-image model, removing manual design bottlenecks.

Core Features & Use Cases

  • Text-to-image generation from prompts to create new visuals without traditional design tools.
  • Image editing and fusion by combining input images with prompts to produce updated visuals.
  • Output handling includes decoding Base64-encoded image data from the API into standard image files for saving and sharing.

Quick Start

Provide a text prompt and optional input images to generate or edit an image using the Gemini 2.5 flash-image model.

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 using the Gemini 2.5 API?▼

To generate images from text prompts using the Gemini 2.5 API, provide a text prompt to the model. The tool uses the google-generativeai SDK to process the request and outputs standard image files decoded from Base64 data.

Can I edit existing images by combining them with text prompts in Gemini 2.5?▼

Yes, you can edit existing images in Gemini 2.5 by supplying optional input images alongside a text prompt. This image fusion workflow updates your visuals based on the prompt instructions.

Do I need a GEMINI_API_KEY to use this image generation tool?▼

Yes, you need a GEMINI_API_KEY set in your environment to use this image generation tool. The key is required by the google-generativeai SDK to authenticate and send requests to the Gemini 2.5 flash-image model.

What is the best way to handle Base64 image data returned by the Gemini API?▼

The best way to handle Base64 image data from the Gemini API is automatic Base64 decoding. This tool decodes the Base64-encoded image data from API responses directly into standard image files for saving and sharing.

How does text-to-image generation with Gemini 2.5 compare to other image editing tools?▼

Text-to-image generation with Gemini 2.5 removes manual design bottlenecks by interfacing directly with the flash-image model. Unlike traditional design tools, it rapidly creates or modifies visuals entirely through prompt-based API integration.

What are the limitations of using prompt-based image editing with the Gemini 2.5 flash-image model?▼

A limitation of prompt-based image editing with the Gemini 2.5 flash-image model is its dependency on external environment configuration. Users must configure the GEMINI_API_KEY and rely on the google-generativeai SDK for request handling.

Related Skills

Explore More Design & Creative Skills→
jdrhynejdrhyne
239

google-ads

Query and manage Google Ads campaigns via the Python SDK or browser automation.

Community
Intermediate
LeoyishouLeoyishou
27

supabase-upload

Upload local files or base64 data to Supabase Storage and return public URLs.

Community
Intermediate
fufuonlinefufuonline

nano-banana-pro

Generate or edit images via Google's Gemini 3 Pro Image API.

Community
Intermediate
All-The-VibesAll-The-Vibes
50

gemini-imagegen

Generate and edit images from text prompts using the Gemini API.

Official
Advanced