transframer-pytorch
transframer-pytorch copied to clipboard
lucidrains
Implementation of Transframer, Deepmind's U-net + Transformer architecture for up to 30 seconds video generation, in Pytorch
Do you need to train it on a specific dataset everytime? Or it is pre-trained so that it can accept any new out-of-the-box series of frames to do next-frame prediction...
This is just a recommendation: When you feel satisfied with your result, post it as a code implementation [here](https://paperswithcode.com/paper/transframer-arbitrary-frame-prediction-with), so that it becomes more popular and easier to find :)
The only semi new thing is the DCT but even that I think is not completely new either. I thought there was already a generative model that did that not...
Metadata
Owner
Metadata
Implementation of Transframer, Deepmind's U-net + Transformer architecture for up to 30 seconds video generation, in Pytorch