Yunhoe, Ku

Results 17 comments of Yunhoe, Ku

> http://www.cs.berkeley.edu/~pathak/context_encoder/resources/inpaintCenterModels.tar.gz you can download directly the file from there. This link is also expired. Where I can download it?

@brianyuastri Did you solve this problem? I have still met this problem :(

Hi, @pfeducode! Did you solve this problem? I also met this problem, but I couldn't solve this problem. If you solve this problem, will you share the any idea?

Did you solve this problem? In my case, it is not still working well like below: ![image](https://github.com/Flode-Labs/vid2densepose/assets/59246456/9a230fc2-8bc2-4d1b-9178-4454c66dd6c0) ![image](https://github.com/Flode-Labs/vid2densepose/assets/59246456/64e9e015-721d-435d-be93-62a31cb76930)

> The part that guide the clothes features such as clothes text and color is the IP-Adapter. People experimented with just IP-Adapter for VTON but ran into the same problem....

Thank you for response, @jacobinu. Actually, I tried to train IP-Adapter (i.e. IPAdapterFull model) by replacing CLIP token to DINOv2 token, but it was not work for me. However, I...

@iloveOREO sorry for bothering you, but I have same question about that equation; `x = s(x_c + \delta)R + t`. Is there any insight about this equation after you questioning?...

@iloveOREO Thank you for the kind replying :smile:

I am more confident with this simple DDP + GAN training, which mimics the problems of current pytorch lightning DDP module: ``` # ----- Combined GAN Module ----- class GANModule(nn.Module):...

Is there any solution for this problem @theoden8 ? I stuck with this problem :(