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

lucidrains/phenaki-pytorch Issues

Clarity on Datasets used for Training!
Updated 2 months ago1
training data
Updated 2 months ago1
Training the Phenaki - RuntimeError: CUDA error: device-side assert triggered
Closed 4 months ago2
cannot reproduce
Closed 4 months ago7
Release pretrained models?
Updated 7 months ago6
Successfully trained the CViViT! Working on the second step
Updated 7 months ago5
Where can find '/path/to/trained/cvivit.pt'
Closed 9 months ago1
Save video?
Updated 10 months ago4
Problem With Multi-GPU Training
Closed a year ago2
When will the code be released?
Updated a year ago2
discriminator loss goes to infinity
Updated a year ago12
Compatibility issue with A100-80G with version 0.0.67
Closed a year ago3
Einops Error. Shape mismatch
Closed a year ago2
Unconditional Training returns errors
Closed a year ago5
What is out of index?
Closed 2 years ago1
In phenaki to output video_codebook_ids...
Closed 2 years ago1
how to run cvivit trainer or phenaki trainer
Closed 2 years ago8
ImportError: T5Tokenizer requires the SentencePiece library but it was not found in your environment.
Closed 2 years ago4
I have a theoretical question about maskgit cross attention
Closed 2 years ago2
Running out of CUDA/GPU spaces
Updated 2 years ago17
model.buffer is EMPTY list in EMA get_buffers_iter function
Closed 2 years ago4
There is error in ema
Closed 2 years ago1
Different video sizes
Updated 2 years ago1
Error in Sample(): Expected scalar type float but found double
Updated 2 years ago7
Some errors that appear on the training results
Closed 2 years ago3
video preprocessing
Updated 2 years ago2
phenaki-pytorch package not found
Closed 2 years ago2
to run C-ViViT...
Closed 2 years ago2
c-vivit return_recons = True with use_vgg_and_gan = True
Closed 2 years ago3
how to condition on text embeddings from T5X
Closed 2 years ago2