Home

Awesome

Indi Model Training Repository

Introduction

This repository contains the code for training the Indi model, an image processing model designed for image to image translation. This is a personal implementation of the Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration (InDI) paper by Delbracio et al 2023. The code is organized into three main files:

Examples

Getting Started

Prerequisites

List of libraries to run the project:

Installation

pip install torch numpy pillow tqdm

Results and Output

This implementation gives you an idea on how the InDI architeture work and it is made up for image to image translation tasks. For more information about it read the paper https://doi.org/10.48550/arXiv.2303.11435

Contact

Contact me at francesco.ramunno@fhnw.ch

References