Premith Kumar Chilukuri

yes, got reasonable results using this code, I had a training dataset of around 3,000 videos in .gif format. Ran till 100000 iterations. During the training process the model parameters...

custom dataset, around 10K training samples

The input & output number of frames are fixed and this parameter can be changed during training/inference, also the current code does not support taking .gifs as condition to generate...

How do you condition (image/gif + text) on a custom input, the model should be loaded from already saved milestones/checkpoints in "./results/" folder. Thank you.

Hi, I have an issue similar to yours's. I have trained the model on a custom data, the milestones/checkpoints are saved in "./results" folder. The training code was straight forward,...

you can use the following code for sampling from trained model parameters: import torch from video_diffusion_pytorch import Unet3D, GaussianDiffusion, Trainer, video_tensor_to_gif batch_size = 1 model = Unet3D( dim = 64,...

follow the below steps to overcome this error: 1) pip3 uninstall setuptools-scm 2) pip3 install setuptools==58.2.0 after this build the model again and you might not face issues