Kyle Sargent

After using the specified view idxs the performance actually seems to drop slightly. RTMV | PSNR | SSIM | LPIPS -- | -- | -- | -- Zero123 (paper) |...

Thanks very much for the response. Regarding the eval code, my implementation is at https://github.com/kylesargent/zero123/blob/e72542d07c13e0aca2809cb26c01c63889e920ea/zero123/ldm/models/diffusion/ddpm.py#L629. I would really appreciate it if you could take a look. The default eval parameters...

I also noticed this issue.

Am also experiencing this; anyone have a fix?

The following disgusting hack via monkey-patching mitigates the issue for me. Basically I define some new methods for my plmodule in question ``` def get_orphans(self): all_tensors = list(get_tensors()) plmodule_tensors =...

Also experiencing this

@takerum In table 8 of the paper, (where the result of 8.6 IS on CIFAR10 is obtained) it says that the model used a gradient penalty if I am reading...