AI Image (VisionScribe) Captioning System

AI Image Captioning System

A lightweight FastAPI web app that generates AI captions from uploaded images, plus a social-ready caption mode with tone, emojis, and hashtags.
Explore the docs »
English

View Repository   |   Report Bug   |   Request Feature

Table of Contents

1. About The Project
   • Built With
   • Features
2. Getting Started
   • Prerequisites
   • Installation
   • Running Locally
3. Usage
4. Troubleshooting
5. Security & Privacy Notes
6. Roadmap
7. Contributing
8. License
9. Contact
10. Acknowledgments

About The Project

This project is a lightweight web app that generates AI captions from uploaded images. It supports a standard caption mode and a social caption mode with tone, emojis, and hashtags.

(back to top)

Built With

• 
• 
• 
• 
• 
• 

(back to top)

Features

• Upload images and generate AI captions
• Social caption mode with tone, emojis, and hashtags
• Clean UI with preview and drag-and-drop upload
• FastAPI backend with vision-language models

(back to top)

Getting Started

Prerequisites

• Python 3.11 (recommended)
• Conda or venv

Installation

1. Clone the repo

   git clone https://github.com/17addisonlin/AI-Powered-Image-Captioning-System.git
   cd AI-Powered-Image-Captioning-System

2. Create and activate an environment

   conda create -n captioning python=3.11 -y
   conda activate captioning

3. Install dependencies

   pip install -r requirements.txt

Running Locally

1. Start the server

   uvicorn main:app --reload

2. Open http://127.0.0.1:8000

(back to top)

Usage

1. Upload an image in Caption mode to get a short description.
2. Switch to Social mode to generate a social-ready caption.
3. Choose tone and toggle emojis/hashtags if desired.

(back to top)

Troubleshooting

• Slow startup: models download on first run; allow extra time.
• Dependency errors: verify you are using the captioning environment.
• Blank caption: try a different image or reduce image size.

(back to top)

Security & Privacy Notes

• Images are processed locally by your server; nothing is uploaded unless you deploy it.
• If you deploy publicly, add authentication and rate limiting.

(back to top)

Roadmap

• Enhance UI, deploy two tabs with its features
• Add mutiple model support, try light and heavy model
• Add dark/white toggle background
• Improve speed of usage

See the open issues for a full list of proposed features and known issues.

(back to top)

Contributing

Contributions are welcome. If you have improvements or bug fixes, please open an issue or submit a pull request.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

(back to top)

License

Distributed under the MIT License. See LICENSE for more information.

(back to top)

Contact

Addison Lin - LinkedIn

Project Link: https://github.com/17addisonlin/AI-Powered-Image-Captioning-System

(back to top)

Acknowledgments

• Best-README-Template
• Hugging Face Transformers
• PyTorch

(back to top)