I am trying to do a faceswap of Adele and the model looks pretty good. However, I am trying to do my convert on a video where she is singing into a microphone which blocks parts of her face for a significant portion of the video. Even though I've manually removed the microphone from the mask area in every frame, it still ends up being super blurry in the converted video which really detracts from the swap even though the face swap itself looks good. Is there any way to improve this?
Got questions or tips about the Conversion process? This is the place to discuss them.
This forum is for discussing tips and understanding the process involved with Converting faces from your trained model.
If you are having issues with the Convert process not working as you would expect, then you should post in the Convert Support forum.
Please mark any answers that fixed your problems so others can find the solutions.
Masking out the mic in the alignments file for the video you are converting (with the manual tool) should suffice. Just make sure you are using the correct mask.
My word is final