Oleksandr Tkachenko

> Oh okay. Thanks for responding. Will there be / is there anyway to provide a set of say, 40 images of the same face to make a better face...

If you really want to add GIF function to SimSwap I came up with two ways to implement it. In both ways you need to modify 3 files in `util`...

> @drzodozo I've tried writing the script that batch process images but for some reason the actual image isn't being processed due to errors. It queues it up and everything...

> Hello, > > I trained a 512 model with VGGFace2 for 390k steps and I got the following video output . I have also attached one of the samples...

> Did you set --Gdeep True ? Even though 400k should be the minimum you should have seen semi normal results with 390k. Make sure your weights have updated properly...

> omg man, can you share it how to train vggface with 512 ? the dataset is 100GB. my colab only can 70gb free. I do not think that he...

> Turn off the mask, and print the results. From the training output, the training should be no problem. The problem may occur with the test code. There may be...

I did a little experiment with the code. If in` videoswap.py` in `line 89` change `swap_result = swap_model(None, frame_align_crop_tenor, id_vetor, None, True)[0]` to `swap_result = swap_model(None, spNorm(frame_align_crop_tenor), id_vetor, None, True)[0]`...

Perhaps some layer from the model does not load or does not load correctly. If we compare it with a screen with a white face, then in addition to high...

> Sent your ckpt to my email, i will check what has happend. I send link on gmail in profile