Songwei Ge

Duplicate dividing in relative positional encoding

1

Hey @lucidrains, thanks for keeping these models implemented. In line 88 https://github.com/lucidrains/video-diffusion-pytorch/blob/f55f1b0824b1be7d2bb555ed7a5d612eff8ad5d0/video_diffusion_pytorch/video_diffusion_pytorch.py#L84-L88 you have `max_exact` as the half of `num_buckets`, whose value was already halved in line 84. I think...

I was trying to reproduce the label-conditioned model on ImageNet and ran into the error in the title. I think this line in the code, https://github.com/CompVis/taming-transformers/blob/9d17ea64b820f7633ea6b8823e1f78729447cb57/taming/models/cond_transformer.py#L242 should be replaced as:...

Training and inference on UCF-101 dataset

1

Hi, congratulations on the acceptance to NeurIPS and thanks for releasing your code! Since UCF-101 is a widely used benchmark for video generation, and I found that you also had...

About content.rdf.u8.gz

3

Hi Lin, Since Dmoz is closed, the file content.rdf.u8.gz cannot be downloaded anymore. Cound you please help me with the dataset? Or do you have any ideas? Thank you very...