You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
It does not work well for pictures/video where a target is talking, mostly because mouth shape is not recognized accurately
so results show some average position comparing to the original, no difference between closed and half closed mouth (for example).
For comparison, analogs like SimSwap/simswap-inference-pytorch give very good results in such scenarios but worse in face similarity
The text was updated successfully, but these errors were encountered:
It does not work well for pictures/video where a target is talking, mostly because mouth shape is not recognized accurately
so results show some average position comparing to the original, no difference between closed and half closed mouth (for example).
For comparison, analogs like SimSwap/simswap-inference-pytorch give very good results in such scenarios but worse in face similarity
The text was updated successfully, but these errors were encountered: