Thomas De

@FrisbeeDog1 I've got it working on new RTX3060, maybe this will help you: conda create -n cuda python==3.8 pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117 pip install imutils==0.5.4 pip install...

You can play with the face parts in util/reverse2original.py Remove #1 which is the face You can find the list of facial parts somewhere in the original github repo

Yes. Just remove 1 and , you have to use the --use_mask option in your commandline.

Yes, mask has soft border.... You can cange iterations from 7 to 1 at line 81 _smooth_mask = SoftErosion(kernel_size=17, threshold=0.9, iterations=7).cuda()_ Look at the image, from left to right: Mask...

Ok. The GUI version is not official. I guess you donwloaded it from my youtube channel? I will check it the next few days

I've tried it myself. It doesn't work as expected. Maybe it's because they they do masking complety different as I do it in my other projects. If I remember correctly,...

👍

There seem to be some connections to other similar projects on github, like HeSer (head swapper) Same thing there, no code or models...

Ok. Mobile faceswap is working quite good. I made minor changes to it: Rescale, crop output, keep audio... Maybe they are not allowed to publish because model is trained using...

using cuda for inference .... do you have enough gpu memory? try shorter video and/or lower resolution. set face batch_size and wav2lip_batchsize to 1