Zongze Wu

icon indicating a website link https://www.cs.huji.ac.il/~wuzongze/ icon indicating an email [email protected]

Results 63 comments of Zongze Wu

Pretrained stylegan2 models

Here are a set of [pretrained checkpoints](https://drive.google.com/drive/folders/1MqCHQ6Yx-eon-3fu1g_AGjpyAUmzH6Jy?usp=sharing) from our lab.

Input shape of image for the classifiers is wrong

We provide codes for running the classifiers in [GetAttribute.py](https://github.com/betterze/StyleSpace/blob/main/GetAttribute.py). Please refer to [DCI](https://github.com/betterze/StyleSpace#dci-metric) '3 annotate the images using pretrained classifers' for how to use the GetAttribute.py. Specifically, in line [67-69](https://github.com/betterze/StyleSpace/blob/main/GetAttribute.py#L67)...

Input shape of image for the classifiers is wrong

Are you using tensorflow gpu version? I believe the error is caused by tensorflow cpu version.

Input shape of image for the classifiers is wrong

I use tf 1.14.

Does it support SDXL?

is there an implementation for SDXL turbo? thx

remove one object and re-rendering

any reply?

stylegan3

Thx for the comments. Is there a way to create an unaligned version of Mega dataset? Since the images do not need to be aligned, maybe we could use more...

How does mamba support cross attention?

@tridao What about interleaving cross-attention layers with Mamba layers? Do you think this is a good idea? Thx a lot.

SPAE code release

same

Question: no release of decoder checkpoint?

I have the same request. Could you share the diffusion model checkpoint? thx a lot.