Jihwan Kim

icon indicating a website link jjihwan.github.io icon indicating an email [email protected]

icon company Seoul National University icon location Seoul, Korea icon location Computer Vision Researcher @ SNU CVLAB | Incoming Student Researcher @ Google DeepMind

Results 6 comments of Jihwan Kim

SVD-T2V weights

+1

TypeError: a bytes-like object is required, not 'NoneType'

@CooLeee Same error :( Did you solve this?

finetune sv3d_u with custom dataset

https://github.com/jjihwan/SV3D-fine-tune it might help you!

About training code

waitter +1 :)

The density_for_timestep_sampling and loss_weighting for SD3 Training！！！

> Thanks a lot. And for my question3: "when we use logit_normal, it based on the RF-setting. So the weight of the loss should be t/(1-t), but the code doesn't...

VAE training code

@zRzRzRzRzRzRzR +1, Thanks!