Can a model be used on two different clips of the same person?

Getting errors or found a bug when converting faces from a trained model? Post about them here


Forum rules

Read the FAQs and search the forum before posting a new topic.

This forum is for reporting errors with the Convert process. If you want to get tips, or better understand the Convert process, then you should look in the Convert Discussion forum.

Please mark any answers that fixed your problems so others can find the solutions.

Locked
User avatar
HawaiianPizza
Posts: 7
Joined: Mon Nov 28, 2022 11:27 am
Has thanked: 2 times
Been thanked: 1 time

Can a model be used on two different clips of the same person?

Post by HawaiianPizza »

Hi,

I'm just trying to clarify another post on here, if you have a video clip of someone talking for ten minutes in reasonably static conditions eg. they are sat down at the same table in the same position and you faceswap the first minute of the video and make a model and alignments, can you not use that same information to convert faceswap minutes 1-2 without having to go through the entire training process again? Is this all down to frame by frame modelling and not really learning anything for future reference? Thanks.

User avatar
bryanlyon
Site Admin
Posts: 793
Joined: Fri Jul 12, 2019 12:49 am
Answers: 44
Location: San Francisco
Has thanked: 4 times
Been thanked: 218 times
Contact:

Re: Can a model be used on two different clips of the same person?

Post by bryanlyon »

When you train a model, you train it on 2 identities. You can then swap ANY videos with those identities. People like to "fine tune" a model on the swap video to make sure it's got the right exposure to that type of content, it's not required though.

Locked