I had to make some changes to get this to work for me:

* Install required packages (updated for 11/02/2022)
pip install .
cd examples/dreambooth
conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.6 -c pytorch -c conda-forge
pip install -r requirements.txt
pip install -U --pre triton
pip install ninja bitsandbytes
conda install xformers -c xformers/label/dev

I changed the torch install to use 0.12 (the OG pastebin installs the latest 0.13, which did not work for me). I also changed xformers to grab the latest version.

* Training file (running with SD 1.5)
1. Get your training script from here (https://github.com/ShivamShrirao/diffusers/tree/main/examples/dreambooth). I used the 8gb one and followed the instructions for configuring DeepSpeed
2. make sure you save your training script with LF line separators and not CRLF
3. Follow the instructions from this step to dump your 1.5 model (https://github.com/ShivamShrirao/diffusers/issues/50#issuecomment-1294854643).
4. Update the training script for the new model. It should look something like:

export MODEL_DIR="/home/arrow/github/diffusers/models/dump"
export VAE_DIR="/home/arrow/github/diffusers/models/dump/vae"
export INSTANCE_DIR="training"
export CLASS_DIR="classes"
export OUTPUT_DIR="out"

accelerate launch train_dreambooth.py \
--pretrained_model_name_or_path=$MODEL_DIR \
--pretrained_vae_name_or_path=$VAE_DIR \
...