lucidrains/phenaki-pytorch
Implementation of Phenaki Video, which uses Mask GIT to produce text guided videos of up to 2 minutes in length, in Pytorch
PythonMIT
Issues
- 10
Is this CViViT implementation causal?
#42 opened by NSavov - 7
Release pretrained models?
#17 opened by CaydenPierce - 0
Meet an error when training the phenaki
#41 opened by levyisthebest - 1
Clarity on Datasets used for Training!
#40 opened by snehasree-sony - 1
training data
#39 opened by 23Rj20 - 2
Training the Phenaki - RuntimeError: CUDA error: device-side assert triggered
#37 opened by LuthandoMaqondo - 7
cannot reproduce
#38 opened by robotNo201 - 5
- 1
Where can find '/path/to/trained/cvivit.pt'
#31 opened by xzwszl - 4
Save video?
#11 opened by ninajlu - 2
Problem With Multi-GPU Training
#30 opened by sezginerr - 2
When will the code be released?
#1 opened by opentld - 12
discriminator loss goes to infinity
#29 opened by 065294847 - 3
- 2
Einops Error. Shape mismatch
#27 opened by 1geek0 - 5
Unconditional Training returns errors
#26 opened by 1geek0 - 1
What is out of index?
#25 opened by 9B8DY6 - 1
In phenaki to output video_codebook_ids...
#18 opened by 9B8DY6 - 8
how to run cvivit trainer or phenaki trainer
#20 opened by 9B8DY6 - 4
ImportError: T5Tokenizer requires the SentencePiece library but it was not found in your environment.
#24 opened by RyuGood0 - 2
- 17
Running out of CUDA/GPU spaces
#14 opened by gmegh - 4
- 1
There is error in ema
#21 opened by 9B8DY6 - 1
Different video sizes
#13 opened by gmegh - 7
- 3
- 2
video preprocessing
#7 opened by 9B8DY6 - 2
phenaki-pytorch package not found
#4 opened by minarainbow - 2
to run C-ViViT...
#5 opened by 9B8DY6 - 3
- 2
how to condition on text embeddings from T5X
#2 opened by 9B8DY6