The fix1 model is having problems working on my device.
Thank you so much for sharing. I'm having the problem and can't use this fix1 model. The system is showing the following error, but the beta7 and beta6 are fine.
"size mismatch for final_layer.video_out.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([96]).
size mismatch for final_layer.audio_out.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([32])."
As already answered on the other thread:
you need to update Comfyui to a recent version (equal or higher than 0.41 i believe), and use the default Load diffusion model node, custom or different checkpoint loaders will not work unless adapted to use the PDD heads of the FastH3 model.