Text To Face

A GAN based Text to face image Generator

Google Colab Link For Backend: https://colab.research.google.com/drive/1Iuo86ubizK6RayEoMJD-h3XVO4w2i0pR?usp=sharing

Demo

Loom Video - https://www.loom.com/share/7c8ea9c1857b425eb2eec5c3fde88fda

Refer this report for more information https://drive.google.com/file/d/1xKCfA2luwf_rvEkriHgT0EePv7OoFAI3/view?usp=sharing

Features

• Landing Page
• Model 1 Base Line Model
• Model 2 VQGAN + CLIP Model
• Voice Assistant for easy navigation

Screenshots

Environment Variables

To run this project, you will need to add the following environment variables to your .env file

VITE_BASELINE_BACKEND_URL

VITE_VQGAN_CLIP_BACKEND_URL

Run Locally

Clone the project

  git clone https://github.com/veerreshr/Text-To-Face-Frontend.git

Go to the project directory

  cd Text-To-Face-Frontend

Install dependencies

  npm install

Start the server

  npm run dev

Roadmap

• Testing

• More better refinement of algorithms

Feedback

If you have any feedback, please reach out to us at veerreshr@gmail.com