
Example tutorial for learn how to install and use Massed Compute
(Starts at 12:58) : https://youtu.be/KW-MHmoNcqo?si=G1WbG-Qw4ujWvOtG&t=778

Register for Massed Compute using the following link I appreicate that a lot:
https://vm.massedcompute.com/signup?linkId=lp_034338&sourceId=secourses&tenantId=massed-compute

We have a special coupon for all GPUs : SECourses

If you want to learn more about GPUs and prices read this link : https://www.patreon.com/posts/126671823

Select RTX A6000 or Better GPU - like L40S or A6000 ADA or A100, H100 or RTX 6000 PRO - the bigger VRAM better for upscalers

Use thinclient or login patreon on Massed Compute to download files on to your Massed Compute

Put everything into a folder in like desktop or downloads

Don't run scripts from inside of synchronization folder 

I recommend just extract zip file into download folder on Massed Compute and run from there

Open a terminal in the folder where you did put the files

To install run below command

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

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

python3 Download_Train_Models.py --model FLUX_Dev --dir /home/Ubuntu/Downloads

To download FLUX Krea DEV run below

python3 Download_Train_Models.py --model FLUX_Krea_DEV --dir /home/Ubuntu/Downloads

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

python3 Download_Train_Models.py --model FLUX_SPRO_Realism --dir /home/Ubuntu/Downloads

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

cd /home/Ubuntu/apps/kohya_ss
source venv/bin/activate
unset LD_LIBRARY_PATH
./gui.sh --listen=0.0.0.0 --inbrowser --noverify