AI Image Captioning App

This is a Next.js web app that uses Google Gemini AI to generate captions for uploaded images. Users can provide their own Gemini API key for privacy and flexibility.

Key Features

Upload an image and get an AI-generated caption
Modern, responsive UI with Tailwind CSS
Settings page to securely store your own Gemini API key (in your browser only)
Debug info for troubleshooting API issues

Tech Stack

Next.js, React, TypeScript
Tailwind CSS
Google Gemini AI

How to Use

Install dependencies: npm install
Start the development server: npm run dev
Open the app: Go to http://localhost:3000 in your browser.
Add your Gemini API key via the Settings page. Your key is stored only in your browser.
Upload an image and click Generate Caption to get your result.

Links

View on GitHub

Why do I need to add my own API key?

Privacy: Your API key is never shared with the app creator or other users.
Security: You control your own usage and quota.
Flexibility: You can use your own Google Cloud project and manage billing/limits.

Troubleshooting

If you see No caption generated or errors, check the Debug Info section for details.
Make sure your API key has access to the Gemini API and the correct model (e.g., gemini-2.5-pro).
If you need help, check the Google Gemini API documentation or your Google Cloud Console.

Project Overview

AI Captioner is a web application that leverages Google Gemini AI to generate descriptive captions for uploaded images. Designed for accessibility and productivity, it features a modern UI, secure API key handling, and real-time captioning. The app is ideal for content creators, educators, and anyone needing quick, accurate image descriptions.

Your API key and data remain private, and the intuitive interface ensures a seamless user experience. Explore the features and try generating captions for your own images!