Converted vid only swaps 1 FPS, so I need to re train
Posted: Thu Mar 23, 2023 8:29 pm
I extracted face A at every 25 frames(because the guide says that too many faces isn't better and 97k was the whole video) and then trained for 170k iterations with face b. I'm not totally done yet as it's still blurry a little but i wanted to convert just as a test. But when I did the faces are only swapped once for every 25 frames. I'm now extracting face A at every frame. Do I need to retrain again or can I just clean up and use the new alignment file?