Thomas De

The source code is no secret, but I think there is no use pulishing it because you need the old Visual Basic 6 IDE to compile or run it. Try...

Thanks. I don't want a competion. ;-) My own versions I'm using have much more options like eg. cut-in cut-out, face enhancement/restoration... Regards

Same problem. Tried different accounts and different colab notebooks. Disconnected between 10 and 20 epochs

At the bottom of the above image: creating deep fakes.


Pretrained models download you find under releases... Weights (model_ir_se50.pth) you find here: https://github.com/LeslieZhoa/DCT-NET.Pytorch/blob/main/utils/download_weight.sh

If this is not outdated now, wav2lip-HQ uses modified faceparsing-mask in a much easier way I think. I've implemented that in some of my projects. Just cloning the parsing folder...

Have you found a solution? I've upgraded today from gtx1050 to rtx3060 but have not tested. RVC working "out of the box" Tpsmm needs to update cuda I think

Next weekend I will setup the new pc.

@FrisbeeDog1 Ok, I just got another project working on RTX3060 (Thin plate spline motion model modded for face swap) Simswap will be next... 1. You can try creating anaconda environment...