WSL was not so hard to set up
WSL was not so hard to set up
Fgenerating prompts for showcase
Fit is hard for many 
Dwsl -d ubuntu
sudo apt install python3.10-venv
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb
sudo dpkg -i cuda-keyring_1.0-1_all.deb
sudo apt-key del 7fa2af80
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb
sudo dpkg -i cuda-keyring_1.0-1_all.deb
sudo apt-get update
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb
sudo apt-get -y install cuda
git clone --recursive https://github.com/bmaltais/kohya_ss.git
chmod +x ./setup.sh
sudo apt update -y
sudo apt install -y python3-tk
sudo apt install software-properties-common -y
sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt update
sudo apt install python3.10 python3.10-venv python3.10-dev
python3 --version
./gui.sh
git branch
git switch sd3-flux.1
source venv/bin/activate
pip install torch==2.4.0+cu124 --index-url https://download.pytorch.org/whl/cu124
pip install torchvision==0.19.0+cu124 --index-url https://download.pytorch.org/whl/cu124
pip install xformers==0.0.27.post2
./gui.sh
sudo apt install python3.10-venv
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb
sudo dpkg -i cuda-keyring_1.0-1_all.deb
sudo apt-key del 7fa2af80
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb
sudo dpkg -i cuda-keyring_1.0-1_all.deb
sudo apt-get update
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb
sudo apt-get -y install cuda
git clone --recursive https://github.com/bmaltais/kohya_ss.git
chmod +x ./setup.sh
sudo apt update -y
sudo apt install -y python3-tk
sudo apt install software-properties-common -y
sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt update
sudo apt install python3.10 python3.10-venv python3.10-dev
python3 --version
./gui.sh
git branch
git switch sd3-flux.1
source venv/bin/activate
pip install torch==2.4.0+cu124 --index-url https://download.pytorch.org/whl/cu124
pip install torchvision==0.19.0+cu124 --index-url https://download.pytorch.org/whl/cu124
pip install xformers==0.0.27.post2
./gui.sh
GitHub
Contribute to bmaltais/kohya_ss development by creating an account on GitHub.
Fcode format it
Falso how do you handle file saving setup?
Dthat is the list of commands I used to set it up
DI save it on a txt
Fit probably cant reach your windows folders
Dyes it can
Fi see so its aim is not isolation
D
Fi see what you mean
D
Fi think i may make seperate tutorial for it
Dby default the windows drives are mounted under \wsl.localhost\Ubuntu\mnt
Dthese are my paths on kohya
Dim using my windows folders
Fi see thanks for info
Dyou welcome
Nthis is literally what i've just been trying to do for the last hour lol - thank you so much!! i got the kohya gui to launch, but am getting cuda errors, so i haven't bothered trying since that's the whole point over using native windows lol. i may try, though, wondering how soon torch fix is coming?
Dwsl -d ubuntu
Dthis command is to enter to the one installed distributions
Dyou have to install it first
D"wsl --install" first
Dthese are the commands I used but is not a tutorial.. some commands only work if you are in the correct path
Nyeah, i know i didn't run the chmod and see some other stuff in there i probably didn't do, or not in the right order so i'll see - tomorrow though, started a big joy caption batch haha
the error i was getting was like the below, plus a couple more similar
Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
the error i was getting was like the below, plus a couple more similar
Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
Dchmod +x ./setup.sh
Dgit switch sd3-flux.1
source venv/bin/activate
pip install torch==2.4.0+cu124 --index-url https://download.pytorch.org/whl/cu124
pip install torchvision==0.19.0+cu124 --index-url https://download.pytorch.org/whl/cu124
pip install xformers==0.0.27.post2
source venv/bin/activate
pip install torch==2.4.0+cu124 --index-url https://download.pytorch.org/whl/cu124
pip install torchvision==0.19.0+cu124 --index-url https://download.pytorch.org/whl/cu124
pip install xformers==0.0.27.post2
Dfor this you must to be in the kohya folder
Done note, I'm not running kohya from the windows file system, I git cloned kohya to the linux file system Ubuntu\home\user\ I use the windows folders to load the models, images and to save the checkpoints but I don't know if you can run kohya from a mounted ntfs drive so I installed it on the Linux virtual hard drive ext4.vhdx that is on C:\Users<YourUsername>\AppData\Local\Packages<DistroPackageName>\LocalState\ext4.vhdx, this is transparent to the user but is something that is good to know
CRunpod instructions not very clear for SwarmUI. I don't understand what to do 
CAlso I don't know how much storage I need to set
Ffix is on the wayt
Fmore than 75% completed
Fi will look to install dev version of torch 2.4.1
Fupload all files inside zip file
Fset storage like min 100 gb
FYouTubeSECourses
In this video, I demonstrate how to install and use #SwarmUI on cloud services. If you lack a powerful GPU or wish to harness more GPU power, this video is essential. You'll learn how to install and utilize SwarmUI, one of the most powerful Generative AI interfaces, on Massed Compute, RunPod, and Kaggle (which offers free dual T4 GPU access for ...
F15:22 How to install latest SwarmUI on RunPod with accurate template selection
16:50 Port setup to be able to connect SwarmUI after installation
17:50 How to download and run installer sh file for RunPod to install SwarmUI
19:47 How to restart Pod 1 time to fix backends loading forever error
20:22 How to start SwarmUI again on RunPod
21:14 How to download and use Stable Diffusion 3 (SD3) on RunPod
22:01 How to setup multiple GPU backends system on RunPod
23:22 Generation speed on RTX 4090 (step speed for SD3)
24:04 How to quickly download all generated images on RunPod to your computer / device
16:50 Port setup to be able to connect SwarmUI after installation
17:50 How to download and run installer sh file for RunPod to install SwarmUI
19:47 How to restart Pod 1 time to fix backends loading forever error
20:22 How to start SwarmUI again on RunPod
21:14 How to download and use Stable Diffusion 3 (SD3) on RunPod
22:01 How to setup multiple GPU backends system on RunPod
23:22 Generation speed on RTX 4090 (step speed for SD3)
24:04 How to quickly download all generated images on RunPod to your computer / device
Fi found the way of generating stylized outputs
F
Fgonna test some different prompts
DPlease also look into cogvideox 5b
Fyep will do
Fclip training improved resemblance
JDr. how many pictures of you did you use for training? is there a good number? i remember you said if you use to many it starts to look less like the person you train?
Fwell i used 15
Fyou can use more too as long as consisten high quality and has different background and clothing and enviroment
Factually i am gonna test this too
Fpreparing a huge dataset
