Skip to content

Latest commit

 

History

History
49 lines (31 loc) · 1.97 KB

README.md

File metadata and controls

49 lines (31 loc) · 1.97 KB
Raw

Anime VAE-GAN WebApp

This is a web application that uses an Anime VAE-GAN model to reconstruct images. The VAE-GAN model is capable of encoding and decoding anime images, allowing you to visualize the reconstructed versions.

Installation

  1. Clone this repository to your local machine:
git clone https://github.com/utkarsh-iitbhu/anime-vae-gan-webapp.git
cd anime-vae-gan-webapp
  1. Install the required Python packages. It is recommended to create a virtual environment before installing the dependencies:
python -m venv venv
source venv/bin/activate   # On Windows, use `venv\Scripts\activate`
pip install -r requirements.txt
  1. Download the pre-trained VAE-GAN model weights: Before running the application, you need to download the pre-trained VAE-GAN model weights and save them as 'vae.pth' in the root directory of the project. You can get the pre-trained model from here.

Usage

To run the web application, use the following command:

uvicorn main:app --host 0.0.0.0 --port 8000

This will start the FastAPI server, and you can access the web application at http://localhost:8000 in your web browser.

Instructions

  1. Access the home page of the web application at http://localhost:8000.
  2. Click on the "Choose File" button to upload an anime image for reconstruction.

image

  1. Click the "Upload" button to submit the image.

image

  1. Wait for the image to be processed and view the original and reconstructed images side by side.

image

  1. Please note that the model is trained on anime images and may not work as expected with other images.