Last active
November 13, 2021 20:54
-
-
Save cadebrown/54052d919ae7153eab6c57aeab6f0a36 to your computer and use it in GitHub Desktop.
install RIFE video upscaler
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
URL_MODEL="https://drive.google.com/file/d/1APIzVeI-4ZZCEuIRE1m6WYfSCaOsi_7_/view" | |
# clone and setup repo | |
git clone https://github.com/hzwer/arXiv2020-RIFE | |
cd arXiv2020-RIFE | |
pip3 install numpy tqdm sk-video torch torchvision opencv-python moviepy | |
# now, try to open the model URL to download... if this doesn't work, manually visit 'URL_MODEL' and unzip it | |
xdg-open "$URL_MODEL" | |
# *** IMPORTANT *** | |
# after this has ran, unzip the model to 'train_log' | |
# then, you should be able to run: | |
python3 inference_video.py --exp=2 --video=$HOME/Videos/YourVideo.mp4 | |
# sometimes, you have to install this for CUDA v11+ | |
pip install torch==1.8.0+cu111 torchvision==0.9.0+cu111 torchaudio==0.8.0 -f https://download.pytorch.org/whl/torch_stable.html | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment