
SECourses TRELLIS - PyTorch 2.13.0 + CUDA 13.0 + Python 3.12

Fast Upload Download Data HuggingFace Tutorial : https://youtu.be/X5WVZ0NMaTg

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

Recommended GPU is RTX PRO 6000 - best F/P and for best performance select H200

But app works with any GPU, the more VRAM it is better

CUDA 13 needs an NVIDIA driver 580 or newer and a GPU of sm_75 or newer
(RTX 20 series and up - Turing, Ampere, Ada, Hopper, Blackwell)

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

Make folder name like 3d_ai - don't use space chacters or special characters in folder paths ever

Don't run scripts from inside of synchronization folder

Move zip file into downloads folder and extract there

requirements_trellis.txt must sit next to Massed_Compute_Install.sh - it holds
every package version

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

To install run below command

chmod +x Massed_Compute_Install.sh
./Massed_Compute_Install.sh

The installer will install everything and download all models automatically

If your download fails for any reason, just run the install command again -
completed files are skipped and partial files resume where they stopped


Usage After Installation:

a. Open a new terminal in the folder where you downloaded and executed the files.

b. Run the following commands for starting the app on a new terminal


unset LD_LIBRARY_PATH
cd TRELLIS
git reset --hard
git pull
export PYTHONWARNINGS=ignore
export HF_HUB_ENABLE_HF_TRANSFER=0
export CUDA_VISIBLE_DEVICES=0
source ./venv/bin/activate
python3 secourses_trellis.py --share --highvram


To only re-download / resume models without touching the installation run:

source ./TRELLIS/venv/bin/activate
python3 DownloadModels.py


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

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