ExponentialML

> You can try to use this [face parsing](https://github.com/zllrunning/face-parsing.PyTorch) repo to get the mask, and blend the original image and swapping image according to the mask. The results by using...

> @ftaker887 Wonderful~~~~~!!!!!!!!!!!!!!! But it will indeed add complexity to the original simswap repo by introducing self training mask model. How about this you create a individual repo named "simswap...

Try following the instructions [here](https://towardsdatascience.com/installing-pytorch-on-apple-m1-chip-with-gpu-acceleration-3351dc44d67c). I'm not sure about onnxruntime and torch compatibility on a Mac, but you're going to have to do a bit of research for anything built...

Great! If you haven't already, reinstall Simswap using [these](https://github.com/neuralchen/SimSwap/blob/main/docs/guidance/preparation.md#installation) instructions, but replace the `conda install pytorch...` lines with your Mac instructions, and let us know if it works.

> i have newbie question, before update on train model im using insightface 0.2.1 python 3.9 and january 2022 pytorch. its still work for swap video (no error) and image...

This is great @kabachuha! Thanks for this PR, and sure we can get in touch.

> @ExponentialML training works, btw Great! Let me know if any you need any assistance getting things up to speed with the new repository changes.

> Yeah, I'd really appreciate help in carrying it over, since you know much better about the mainline changes By all means. Just let me know when it's ready to...

ModelScope's implementation is very similar to theirs in the sense that they add a temporal dimension to the model. For long video generation, you could follow this PR which uses...

> Many thanks. Do you have any recommendations for AI video flicker removal? No problem! There was a paper released somewhat recently that supposedly tackles this problem, but I can't...