He Cao

How to understand the positional embedding part in rvt(rotary embedding)?

2

Hi, I'm just curious about the different implement way between the `AxialRotaryEmbedding` and the original ones. Since I notice u multiply the pi when calculating sin and cos vector. But...

Hi When I check this line, I thought that to make sure the spatial size won't change, the padding value should be consistent with the dilation value. Since `kernel_size =...

When will release cond-LDM inference scripts?

1

Hi, very impressive work. But despite SR and inpaint task, when will release more interesting conditional inference scripts? Looking forward to these

when will release the BiART training part?

4

Very impressive work! Just wonder when will release the remaining codes

https://github.com/sangyun884/blur-diffusion/blob/9dd8adb917bf4dbb807156382320df14fff502da/blur_diffusion.py#L40 this will cause `self.betas` has `N+1` length, which not consistent with other noise schedule settings

GO Bro !

8

The first action after I saw the paper is: go to GitHub, search 'lucidrains/make-a-video' GO Bro! cannot wait to reproduce this!

Should be `loss * self.eps/(c-1)`?

1

Hi, Based on my understanding, the label smooth loss should be constructed like: for the non-target label, the corresponding value should be set as `\epsilon / (num_classes-1)` https://github.com/ZhugeKongan/torch-template-for-deep-learning/blob/4a84444066456c7bb27daeec5e85d512eccc88cf/autoaug/label_smoothing.py#L19 So, this...

Hi, I just wonder whether here should be `F.pad(kernel, [W_pixels_to_pad, W_pixels_to_pad, H_pixels_to_pad, H_pixels_to_pad])`, since the F.pad's padding mode should be set as `[padding_left, padding_right, padding_top, padding_bottom` https://github.com/DingXiaoH/DiverseBranchBlock/blob/cd627d5089eaa25dedaa258b189fde508586a2f7/dbb_transforms.py#L44 Best

StyleAdapter training datasets?

3

Just curious about how to construct the style pairs? any mature public datasets available?