StableDiffusion-WSL

== https://github.com/ShivamShrirao/diffusers/tree/main/examples/dreambooth ==

* Make a place for downloads
mkdir Downloads
cd Downloads

* Download & Install Anaconda
wget https://repo.anaconda.com/archive/Anaconda3-2022.05-Linux-x86_64.sh
chmod +x ./Anaconda3-2022.05-Linux-x86_64.sh
./Anaconda3-2022.05-Linux-x86_64.sh

* Nvidia CUDA toolkit for Ubuntu WSL - https://developer.nvidia.com/cuda-downloads
wget https://developer.download.nvidia.com/compute/cuda/repos/wsl-ubuntu/x86_64/cuda-wsl-ubuntu.pin
sudo mv cuda-wsl-ubuntu.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget https://developer.download.nvidia.com/compute/cuda/11.7.1/local_installers/cuda-repo-wsl-ubuntu-11-7-local_11.7.1-1_amd64.deb
sudo dpkg -i cuda-repo-wsl-ubuntu-11-7-local_11.7.1-1_amd64.deb
sudo cp /var/cuda-repo-wsl-ubuntu-11-7-local/cuda-*-keyring.gpg /usr/share/keyrings/
sudo apt-get update
sudo apt-get -y install cuda

* New shell with Anaconda & install g++
bash
sudo apt install build-essential

* New virtual Python environment
conda update -n base -c defaults conda
conda create --name diffusers python=3.9
conda activate diffusers

* Make a directory for all your github downloads, then download diffusers
mkdir ~/github
cd ~/github
git clone https://github.com/ShivamShrirao/diffusers.git
cd diffusers

* Install required packages
pip install .
cd examples/dreambooth
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116
pip install -r requirements.txt
pip install -U --pre triton
pip install ninja bitsandbytes
pip install git+https://github.com/facebookresearch/xformers@1d31a3a#egg=xformers

* Configure / login
accelerate config
huggingface-cli login
mkdir -p training
mkdir -p classes
explorer.exe .

* Edit your training file and add this line to the top or reboot:
export LD_LIBRARY_PATH=/usr/lib/wsl/lib:$LD_LIBRARY_PATH

* Copy your training file from your Windows desktop (or wherever you saved it):
cp /mnt/c/Users/YOUR_USERNAME/Desktop/my_training.sh ./
chmod +x ./my_training.sh
./my_training.sh


* NB: If you get an error like this -
403 Client Error: Forbidden for url: https://huggingface.co/CompVis/stable-diffusion-v1-4/resolve/main/model_index.json

Then:
Make sure you've visited https://huggingface.co/CompVis/stable-diffusion-v1-4 and accepted the licence!
NB. If this is the very first time you've used diffusers, it's about a 6GB download

To train again next time, simply:

* Start Ubuntu, then:
conda activate diffusers
cd ~/github/diffusers/examples/dreambooth
./my_training.sh

If someone has problems with CUDA not being detected, just be sure to add "export LD_LIBRARY_PATH=/usr/lib/wsl/lib:$LD_LIBRARY_PATH" to the train file.
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 \
...