When Rendering the Pretrained Models Only Renders White or Black

[Stelath]

When loading visualizer.py everything works fine until I load the model where it only renders black with a few artifact pixels on the side and some random RGB colored pixels when I move it around:

However when I switch to superresolution.block0.conv0 I can see the convolutions on some sort of face, which makes me believe that there is a problem with the upscaler:
Screencast from 11-17-2022 11:36:50 AM.webm

This is my render.ray_marcher layer as well:

Also here is my console output:

python visualizer.py 
/home/stelath/miniconda3/envs/eg3d/lib/python3.8/site-packages/scipy/__init__.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.23.4
  warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
Loading "https://api.ngc.nvidia.com/v2/models/nvidia/research/eg3d/versions/1/files/ffhq512-128.pkl"... Done.
Setting up PyTorch plugin "bias_act_plugin"... Done.
Setting up PyTorch plugin "upfirdn2d_plugin"... Done.

[Stelath]

I have also tried different models, downloaded the pretrained models manually, and even tried to run Sytle GAN 3 (as the code for the visualizer uses Style GAN 3 extensions) but that also had a similar problem, I think its probably something to do with my hardware or dependencies.

Also I'm using a 1660 Ti, though I did get it to run on an V100

[Stelath]

Update it looks as if the .torgb blocks in the super resolution nn could be to blame.