Xu Minghui

Results 7 comments of Xu Minghui

why p_mean_variance use noise_level instead of sample_gammas like in training for time conditon of denoise function.

I have the same question. Did you find the reason?

why p_mean_variance use noise_level instead of sample_gammas like in training for time conditon of denoise function.

> #50 i think the author explain this in here. Got it. Thanks~

what's the valid mask

So, I think we need to define a new function in 'mask.py' to load our own masks, right? And I'm wondering if this generative way can maintain the diversity (that...

AutoEncoderKL output tensor dimension mismatch with Input

I believe this is caused by downsampling and upsampling on data with a nan 2 power dimension.

test noise schedule and train noise schedule are different?

Thank you so much!

Joint training of VAE and Transformer

> [@minghuix98](https://github.com/minghuix98) hey Xu, at the moment not, but i could make it customizable next week if you have that need Hi Phil Wang, Thanks so much for your prompt...

Joint training of VAE and Transformer

> [@minghuix98](https://github.com/minghuix98) hmm, correct me if i'm wrong, but REPA depends on a pretrained DINO? i'm not sure if it can be applied here if so Yeah, it's correct! And...