>Consistent video style transfer is something any good nerd would be interested in, and so CoDef is certainly a pretty cool addition to the variety of tools out there already. Style a single frame and you’ve styled your entire video clip. Excellent. Just how we like it!

Quite a long tutorial this one, but you’ll earn your nerd wings by the end 🙂

New Python 3.10 environment:
conda create –name Your EnvName python=3.10

Making a CUDA 11.8 environment:
conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia
conda install -c “nvidia/label/cuda-11.8.0” cuda-nvcc
conda install -c “nvidia/label/cuda-11.8.0” cuda-toolkit

Video-to-frames example for ffmpeg:
ffmpeg -r 25 -i input.mp4 -start_number 0 -pix_fmt rgb24 ./all_sequences/Nerdy/Nerdy/%5d.png

== Links! ==
CoDef – https://github.com/qiuyu96/CoDeF
tiny-cuda – https://github.com/NVlabs/tiny-cuda-nn
S&TA – https://github.com/z-x-yang/Segment-and-Track-Anything
CoDef Colab – https://github.com/camenduru/CoDeF-colab
Example video – https://pixabay.com/videos/wood-anemones-wildflower-flower-112429/
Automatic1111 Web UI – https://github.com/AUTOMATIC1111/stable-diffusion-webui
ControlNet Extension – https://github.com/Mikubill/sd-webui-controlnet
Anaconda – https://www.anaconda.com/

= Fun Playlists! =
* Stable Diffusion Playlist! – https://youtube.com/playlist?list=PLjC8P1vEncQDVOC1GgkT3chdyTSs0f9Z />* Interested in adding things to your AI Art? Try these!
Dreambooth Playlist –
https://youtube.com/playlist?list=PLjC8P1vEncQD-QYBsYcyYq9JUAxQSZXnW />* Textual Inversion Playlist – https://youtube.com/playlist?list=PLjC8P1vEncQDSDLKuPAEguajtdVKZpr9Y

Support the Hairy Eyeball

Share this on