Virtual Try-On is an application that allows you to virtually try on clothes using Google's advanced image generation models on Vertex AI.

With just an image of a person and a product, you can generate high-quality photos of the person wearing the item.

• Realistic Previews: Generate high-quality, realistic images of people wearing different apparel.
• Support for Various Products: Works with tops, bottoms, and footwear.
• Customizable Generation: Adjust parameters like quality and the number of generated images.
• Simple Web Interface: Easy-to-use interface built with Gradio.

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

• Python 3.13+
• uv (a fast Python package installer and resolver)
• just (a handy command runner for automating tasks)

1. Clone the repository:

   git clone https://github.com/fmind/virtual-try-on.git
   cd virtual-try-on

2. Install the dependencies: Use the just command to install all required packages.

   uv sync

Once the installation is complete, you can start the Gradio web interface:

just app

Open your web browser and navigate to the URL provided in the console (usually http://127.0.0.1:7860).

This project uses just to simplify common development tasks.

• Check Code Quality:

  just check

  This will run linting, formatting checks, type checking, and unit tests.

• Format Code:

  just format

  This will automatically format the code to match the project's style.

• Clean Up:

  just clean

  This will remove temporary files and caches.

You can also build and run the application using Docker.

1. Build the Docker image:

   just docker-build

2. Run the Docker container:

   just docker-run

   This will start the application on port 8080.

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