Setup Instructions (Python 3.10.11, 4090, working on Windows):
Go to user directory
right click git bash
git clone https://github.com/Stability-AI/generative-models.git

-modify streamlit_helpers.py
lowvram_mode = True

move video_sampling.py file to main dir
create a checkpoints folder in the main dir
download the SVD weights from https://huggingface.co/stabilityai/stable-video-diffusion-img2vid/tree/main
(optional) donwload SVD-XT weights from https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt/tree/main

-modify requirements/pt2.txt file
remove triton==2.0.0 line and save

-modify requirements/pt13.txt file
remove triton==2.0.0.post1 line and save

Open Anaconda
cd to user/generative-models
conda create -n genModelVideo python=3.10.11
conda activate genModelVideo


pip install https://huggingface.co/r4ziel/xformers_pre_built/resolve/main/triton-2.0.0-cp310-cp310-win_amd64.whl
pip install -r requirements/pt2.txt
pip install .
pip install -r requirements/pt13.txt


streamlit run video_sampling.py

click "Load Model"

upload image and there you go.

Will get a tensor error but you can ignore it. Still seems to work

*try 48 decode t frames for faster generation