video-diffusion-pytorch icon indicating copy to clipboard operation
video-diffusion-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon lucidrains

Training Dataset

Open Mq-Zhang1 opened this issue 2 years ago • 2 comments

Hi, thanks for this fantastic work!

Could I ask what is the training dataset for text-to-video generation? And any training code provided for this task?

Thank you so much

Mq-Zhang1 avatar Apr 23 '22 07:04 Mq-Zhang1

Looking forward to the dataset as well. If this dataset cannot be released now, could you kindly tell us how does this dataset constructed, e.g., the captions are manually labeled or extracted from pretrained networks?

zhuhaozh avatar May 09 '22 02:05 zhuhaozh

Anyone has an idea what kind of public dataset we can use to test except the moving MNIST? The public dataset should also contain the respective annotations.

oxjohanndiep avatar Jul 15 '22 03:07 oxjohanndiep