stylegan-xl
stylegan-xl copied to clipboard
Setting for the pretrained models?
Hello! I'm trying to fine tune the FFHQ pretrained model on another dataset. Unfortunately, it fails with the following error:
RuntimeError: output with shape [12] doesn't match the broadcast shape [12, 12]
I wonder if the model has been trained with specific settings, which then don't work for out of the box fine tuning?
- #19