README.md

metadata

title: Virtual Try-On App
emoji: 👕
colorFrom: blue
colorTo: green
sdk: docker
app_port: 8000
pinned: false

Advanced Virtual Try-On

A web-based virtual try-on application that allows users to try on clothing virtually using their webcam. Built with Python, OpenCV, and Shiny.

Features

• Real-time virtual try-on using webcam
• Support for transparent background garment images
• Adjustable garment fitting parameters
• Multiple UI modes (Shiny web interface, Tkinter desktop app)
• Docker support for easy deployment

Prerequisites

• Python 3.9 or higher
• Docker and Docker Compose (for containerized deployment)
• Webcam
• OpenPose models (will be downloaded automatically on first run)

Installation

Local Development

1. Clone the repository:

git clone <repository-url>
cd virtual-tryon

2. Create a virtual environment and activate it:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

Docker Deployment

1. Build and run using Docker Compose:

docker-compose up --build

The application will be available at http://localhost:8000

Usage

Web Interface (Shiny)

1. Start the application:

python app.py --shiny

2. Open your web browser and navigate to http://localhost:8000

3. Upload a garment image with transparent background

4. Click "Start Try-On" to begin the virtual try-on session

5. Adjust the garment fit using the sliders:

   • Width Scale: Adjust the width of the garment
   • Height Scale: Adjust the height of the garment
   • Collar Position: Adjust the vertical position of the garment
   • Show Skeleton: Toggle the display of pose estimation skeleton

Desktop Application (Tkinter)

1. Start the application:

python app.py --tkinter

2. Use the GUI controls to upload a garment and adjust parameters

Command Line Mode

1. Run with a specific garment:

python app.py --garment path/to/garment.png

Directory Structure

• models/: Directory for storing OpenPose models
• temp/: Directory for temporary files
• app.py: Main application file
• requirements.txt: Python dependencies
• Dockerfile: Container configuration
• docker-compose.yml: Docker Compose configuration

Troubleshooting

1. Webcam not detected:

   • Ensure your webcam is properly connected
   • Check if the webcam is being used by another application
   • For Docker deployment, ensure proper device access is configured

2. Garment not displaying correctly:

   • Use images with transparent backgrounds (PNG format recommended)
   • Ensure the garment image is not too large or too small
   • Try adjusting the width and height scales

3. Performance issues:

   • Reduce the camera resolution
   • Close other resource-intensive applications
   • For Docker deployment, ensure proper resource allocation

License

This project is licensed under the MIT License - see the LICENSE file for details.