
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

When deploying a Pod select any GPU but min RTX 3090 i recommend - 24 GB - RTX 5090 best

select runpod template - this is important

RunPod Pytorch 2.2.0
runpod/pytorch:2.2.0-py3.10-cuda12.1.1

Edit Template

Make volume disk 50 gb  min

Add expose HTTP ports 7861 to connect via proxy if you want but i recommend Gradio share

It will by defualt start with --share with gradio share as well

Upload everything into workspace folder - you can upload zip file and extract it as well

To install run below command

export HF_HOME="/workspace"
chmod +x RunPod_Install.sh
./RunPod_Install.sh

After running the app it will download few additional models

Just run the app again if your download fails for any reason

To use after install

Open a new terminal and run below code to start every time

unset LD_LIBRARY_PATH
cd /workspace/sam-3d-objects
export HF_HOME="/workspace"
export PYTHONWARNINGS=ignore
git reset --hard
git pull
source ./venv/bin/activate
python demo_gradio.py --share

To kill previously running app without restarting the machine run below command

apt update
apt install psmisc
for p in $(seq 7860 8000); do fuser -k ${p}/tcp 2>/dev/null; done
