

SIMPLEPOD CHEAPER AND FASTER THAN RUNPOD

Now we fully support SimplePod as well please use this link to register : https://simplepod.ai/ref?user=secourses

SimplePod is faster and cheaper than RunPod and works exactly same

Please use this template on SimplePod : https://dash.simplepod.ai/account/explore/100/ref-secourses/

For permanent storage, generate it from Storage tab with any name and size you want and when selecting template with above link, click Edit and Use, select Persistence Volume and change mount point to /workspace

Up-to-date SimplePod tutorial starting from 21:51 : https://youtu.be/yOj9PYq3XYM?si=Z86wZZLBeYzWo1Qo&t=1311

RUNPOD

Please register for RunPod at: https://get.runpod.io/955rkuppqv4h

Example tutorial for learn how to install and use RunPod is below

(starts at 22:03) : https://youtu.be/KW-MHmoNcqo?si=QN8X8Sjn13ZYu-EU&t=1323

RunPod permanent network storage tutorial : https://youtu.be/8Qf4x3-DFf4

Select this template mandatory (based on official Runpod Pytorch template) : https://get.runpod.io/SECourses_CU13

Port 3000 is auto exposed to connect ComfyUI and you can literally use with any available on GPU on RunPod

You can edit template and change Volume Disk size. it is by default 200 GB

Upload all files into workspace extract all from zip file or directly upload extracted files

Start a new terminal

Copy paste below command and it will install and start Kohya SS GUI for FLUX with newest drivers and libraries

pip install huggingface_hub requests hf_xet
chmod +x RunPod_Install_Kohya.sh
./RunPod_Install_Kohya.sh

The rest of the usage is same as other previous tutorials

Also you can execute below commands to download all necessary models quickly into workspace

You can download them while installing with a new terminal window. You can use any of base models as FLUX Dev or FLUX Krea or FLUX SRPO

FLUX SRPO is most realistic one for training

To download FLUX DEV run below

python Download_Train_Models.py --model FLUX_Dev --dir /workspace

To download FLUX Krea DEV run below

python Download_Train_Models.py --model FLUX_Krea_DEV --dir /workspace

To download FLUX SRPO run below - SRPO is really realistic model

python Download_Train_Models.py --model FLUX_SPRO_Realism --dir /workspace

Then you can set their paths on GUI check Example Full Setup.jpg

In RunPod don't forget /workspace "/" in beginning

The install will auto start the Kohya but to run it afterwards run below

apt update --yes
yes | apt-get install python3.10-tk
apt-get install psmisc --yes
fuser -k 7860/tcp
cd /workspace/kohya_ss
source venv/bin/activate
unset LD_LIBRARY_PATH
./gui.sh --listen=0.0.0.0 --share --noverify