kashif/minRF

Minimal Implementation of Rectified Flow

Left is the naive RF, right is the logit-normal time-sampling RF. Both are trained on MNIST.

This repository contains a minimal implementation of the rectified flow models. I've taken SD3 approach of training along with LLaMA-DiT architecture. Unlike my previous repo this time I've decided to split the file into 2: The model implementation and actual code, but you don't have to look twice.

Everything is still self-contained, minimal, and hopefully easy to hack. There is nothing complicated goin on if you understood the math.

1. Simple Rectified Flow, for beginners

Install torch, pil, torchvision

pip install torch torchvision pillow

Run

python rf.py

to train the model on MNIST from scratch.

If you are cool and want to train CIFAR instead, you can do that.

python rf.py --cifar

On 63'th epoch, your output should be something like:

2. Massive Rectified Flow

This is for gigachads who wants to train Imagenet instead. Don't worry! IMO Imagenet is the new MNIST, and we will use my imagenet.int8 dataset for this.

First go to advanced dir, download the dataset.

cd advanced
pip install hf_transfer # just do install this.
bash download.sh

This shouldn't take more than 5 min if your network is decent.

Run

bash run.sh

to train the model. This will train Imagenet from scratch.