SECourses_Musubi_Trainer_Setup / Runpod_SimplePod_Musubi_Trainer_Instructions.txt
nanaj's picture
Upload folder using huggingface_hub
5e296ef verified
Raw
History Blame Contribute Delete
2.17 kB
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
To install run below command
pip install huggingface_hub requests
export HF_HOME="/workspace"
chmod +x RunPod_Install_Musubi_Trainer.sh
./RunPod_Install_Musubi_Trainer.sh
To automatically download training models into /workspace folder open a new terminal in the folder and execute below commands
You can run this command same time as installation with opening another terminal
Then download models (choose which model you want):
python Download_Train_Models.py
This above command will ask you which model to download choose from menu
To run the app again after installation later run below command - installation will auto start the app so use this later for re-starting the app
cd /workspace/SECourses_Musubi_Trainer
git pull
source venv/bin/activate
unset LD_LIBRARY_PATH
python gui.py --share