NailVirtuoso: AI-Powered Virtual Nail Try-On: NailVirtuoso is an AI-powered web application that allows users to virtually try on different nail colors. By uploading an image of their hand, a U-Net deep learning model performs precise nail segmentation, and the user can select any color to see it applied in real-time. This project was developed for the TensorForge '25 AI Buildathon.
Features
AI-Powered Nail Segmentation: Utilizes a U-Net architecture for accurate nail detection.
Virtual Color Try-On: Apply any selected color to the segmented nails on your uploaded photo.
Web-Based Interface: Easy-to-use application accessible from any web browser.
Containerized Deployment: Packaged with Docker for easy and reproducible setup.
Local Setup Instructions
Follow these steps to set up and run the project on your local machine.
Prerequisites
Python 3.9 or later
pip for package management
A virtual environment tool (like venv)
Installation
Clone the repository:
Bash
git clone https://github.com/your-username/nailvirtuoso.git cd nailvirtuoso Create and activate a virtual environment:
Bash
For Windows
python -m venv venv .\venv\Scripts\activate
For macOS/Linux
python3 -m venv venv source venv/bin/activate Install the required dependencies:
Bash
pip install -r requirements.txt Download the pre-trained model: Ensure your trained model file (nail_segmentation_model.pth) is located in the model/ directory.
Running the Application
Start the Flask server:
Bash
python run.py Access the application: Open your web browser and navigate to http://127.0.0.1:5000.
Docker Deployment
The easiest way to run this project is by using Docker.
Prerequisites
Docker Desktop installed and running.
Quickstart with Docker
Build the Docker image: From the project's root directory, run the following command:
Bash
docker build -t nail-virtuoso . Run the Docker container: This command will start the application and make it accessible on port 5001 of your local machine.
Bash
docker run -p 5001:5000 nail-virtuoso Access the application: Open your web browser and navigate to http://localhost:5001.
Project Structure
. ├── model/ │ └── nail_segmentation_model.pth ├── notebooks/ │ └── data_exploration.ipynb ├── scripts/ │ └── Model Train Stage (it contain code bases and some samll amount of data I use to train models) | └── Running_Stage (here is the working code bases) ├── Dockerfile ├── README.md ├── requirements.txt └── run.py └── Demo Video.mp4