📋 Table of contents
The aim of this project is to create our own Deep Learning model that generates brand new car images. We develop our home-made unconditional image generation model based on the paper Denoising Diffusion Probabilistic Models from Jonathan Ho, Ajay Jain, Pieter Abbeel in 2020. We followed the structure of the article and implemented main function to recreate an unconditional image generator, based on the diffusion process.
- Ensure that git is installed on your machine. Download Git
- Docker is used for the backend and database setup. Download Docker
git clone https://github.com/CogitoNTNU/DiffusionModel.git
cd DiffusionModeldocker compose up --buildThen navigate to http://localhost:8501 in your browser to access the UI of the frontend.
Done! You are now ready to generate cars!
The team behind this project is a group of students at NTNU in Trondheim, Norway, developed during the spring semester of 2024.
 Marijan Soric |
 Thomas Haslund Wik |
 Mauritz Skogøy |
 Amanda Truyen |
 Baris Batur |
This project would not have been possible without the hard work and dedication of all of the contributors. Thank you for the time and effort you have put into making DiffusionModel a reality.
Left to right: @BarisBatur, @soricm (Team leader), @amandathunes, @Mauritzskog. (@ThomasHWik isn't in the picture)
Distributed under the MIT License. See LICENSE for more information.