Want to know about the Faceswap's Face Extraction process? Got tips, ideas or just want to learn about how it all works? Then this is the place for you
This forum is for discussing tips and understanding the process involved for Extracting and preparing face sets for training a model in Faceswap.
If you have found a bug are having issues with the Extraction process not working, then you should post in the Extract Support forum.
Please mark any answers that fixed your problems so others can find the solutions.
I am very new to faceswap so apologies if this is a trivial question. I have done a bunch of ML in the past so I am familiar with the general flow.
My question is related specifically to this line in the "Extract" tutorial:
"If you are extracting for convert, or you are extracting for convert AND will be using some of the faces for training, then leave this on 1 (i.e. extract from every frame)".
As I understand it, I need to extract both Video A (the face I am removing) and Video B (the face I am inserting). However, what does it mean in the above if I am "extracting for convert and using some of the faces for training"?
Logically, it seems to me that for Video A I need to use N=1 because I need to cut the face out for every frame. For Video B, Should I use N = 12 or N= 15 then? As on a 60 FPS video I don't need every single frame? Thanks in advance for your help!
- Site Admin
- Posts: 622
- Joined: Fri Jul 12, 2019 12:49 am
- Location: San Francisco
- Has thanked: 3 times
- Been thanked: 159 times