are models in faceswap just architecture or pre-trained

Want to understand the training process better? Got tips for which model to use and when? This is the place for you


Forum rules

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

This forum is for discussing tips and understanding the process involved with Training a Faceswap model.

If you have found a bug are having issues with the Training process not working, then you should post in the Training Support forum.

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

Locked
User avatar
damingxing
Posts: 23
Joined: Mon Jun 13, 2022 8:55 pm
Has thanked: 6 times

are models in faceswap just architecture or pre-trained

Post by damingxing »

out of curiosity, for the models from faceswap (iae, villain, phaze-a...)

  1. are they just architecture, meaning we train them with our data from scratch (starting from random weights)?
    or
  2. are they pre-trained models; we are just fine-tunning them with our data (videos)?

Thanks!

by torzdf » Wed Aug 17, 2022 8:44 am

You are training them from scratch, unless you choose to load/freeze weights from a previously trained model.

Go to full post
User avatar
torzdf
Posts: 2651
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 129 times
Been thanked: 622 times

Re: are models in faceswap just architecture or pre-trained

Post by torzdf »

You are training them from scratch, unless you choose to load/freeze weights from a previously trained model.

My word is final

Locked