video-diffusion-pytorch
video-diffusion-pytorch copied to clipboard
Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch
Hello, I train the model based on text conditioning but I don't really understand what I need to do to train the model for several epochs We basically have 3...
Hi. Thanks for your work. I want to train this model with my own dataset. I wonder what is this dataset structure? What structure form should I set the dataset?...
Hi, Thanks for this amazing work. I want to use this model to perform class-conditioned video generation instead of text-conditioned, is it possible with this repo? Thanks in advance
In this [groupnorm](https://github.com/lucidrains/video-diffusion-pytorch/blob/main/video_diffusion_pytorch/video_diffusion_pytorch.py#L180), the norm seems to be applied over time dims too, ie. it is not fully time factorised
I ran this in google collab but when it completed there was no `results` directory. Do you know where to find the result if using google collab?
one called SpatialLinearAttention, the other is normal attention.
Is there any pertrained model?
Hi, my issue was not really significant to open a thread. I just want to know how to display final sampled_videos using matplotlib, i'm permuting (channels, frames, height, width) using...
`--timesteps 256 --loss_type l2 --train_lr 0.0003 --beta2 0.99 --train_num_steps 600000 --train_batch_size 16 --gradient_accumulate_every 4 --ema_decay 0.9999 --base_channel_size 256 --image_size 64 `
I have been working on your video diffusion code from the past 5 months, your code base helped me a lot, thank you. I thought it would be beneficial, if...