Adding extra faces after extraction?

The Extraction process failing on you, and you aren't getting an error back with clear instructions? Tell us about it here


Forum rules

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

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

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

Locked
User avatar
Morkerflat
Posts: 5
Joined: Mon Jan 17, 2022 2:37 pm

Adding extra faces after extraction?

Post by Morkerflat »

So I'm new and still in the testing phase,

I did my first swap and turned out ok-ish but I read that you need to add as many pics from different angles and lighting if possible.

So what I did was Extract from vid A and then extract from vid B and the put face B in video A (without using alignments I believe since im new)

Now my question is, after extracting from vid B can I add additional face pics not from Vid B itself and put them in faceB folder to add more variety and options for the program to train?

User avatar
abigflea
Posts: 182
Joined: Sat Feb 22, 2020 10:59 pm
Answers: 2
Has thanked: 20 times
Been thanked: 62 times

Re: Adding extra faces after extraction?

Post by abigflea »

If I am following you correctly, then yes for training data.
The alignments are stored in in the extracted data/photos you can just add and subtract from the folder.

Be sure you keep the mask generation the same, to avoid any weirdness.

:o I dunno what I'm doing :shock:
2X RTX 3090 : RTX 3080 : RTX: 2060 : 2x RTX 2080 Super : Ghetto 1060

Locked