[Newbie] Can I change model on training?

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.

Post Reply
User avatar
adriadg
Posts: 8
Joined: Sat Sep 02, 2023 10:32 am
Has thanked: 3 times

[Newbie] Can I change model on training?

Post by adriadg »

Hi guys,

I have start training with my faces using the "original" model. After several hours and more than 100k iterations, results are weak and blur, so I have read that using Phaze-A model will be the most proabable solution to that.

My question is: if I start using this new model, my previous training seasons are useless? Or the software use both results to improve the final result on conversion?

thanks

Last edited by adriadg on Tue Sep 05, 2023 11:27 am, edited 1 time in total.
User avatar
torzdf
Posts: 2621
Joined: Fri Jul 12, 2019 12:53 am
Answers: 155
Has thanked: 128 times
Been thanked: 610 times

Re: [Newbie] Can I change model on trainning?

Post by torzdf »

If you change the model, you have to start again. Different models are not directly compatible with each other.

Also, see here: I've trained the model for ages, the previews look good, so why is the swapped face blurry?

My word is final

User avatar
adriadg
Posts: 8
Joined: Sat Sep 02, 2023 10:32 am
Has thanked: 3 times

Re: [Newbie] Can I change model on training?

Post by adriadg »

thanks!

User avatar
williamshane
Posts: 1
Joined: Wed Jan 31, 2024 2:21 am

Re: [Newbie] Can I change model on trainning?

Post by williamshane »

torzdf wrote: Tue Sep 05, 2023 8:47 am

If you change the model, you have to start again. Different models are not directly compatible with each other.

Also, see here: I've trained the model for ages, the previews look good, so why is the swapped face blurry?geometry dash

This is a problem that I am also experiencing. How am I supposed to go about fixing it? The link you provided led me to it.

Last edited by williamshane on Mon Feb 05, 2024 8:43 am, edited 1 time in total.
User avatar
torzdf
Posts: 2621
Joined: Fri Jul 12, 2019 12:53 am
Answers: 155
Has thanked: 128 times
Been thanked: 610 times

Re: [Newbie] Can I change model on trainning?

Post by torzdf »

williamshane wrote: Thu Feb 01, 2024 11:31 am

This is a problem that I am also experiencing. How am I supposed to go about fixing it? The link you provided led me to it.

Not sure what you are asking, but the FAQ item in question is this one:

https://forum.faceswap.dev/app.php/faqpage#f4r1 wrote:

I've trained the model for ages, the previews look good, so why is the swapped face blurry?
There are many reasons that this can happen, the main ones are:

  • You are training a low resolution model and are trying to swap on to a close-up in a high resolution image. Some of the older models (for example Original and Lightweight) train to a 64 pixel output size. Stretching a 64 pixel image onto a higher resolution output is always going to be blurry, no matter what you do, as the data just won't exist in the swapped image to pad out sharp data.
  • Your data variety you used for training is bad. Data variety is the single most important thing for achieving a good swap. Lots of very similar data with very similar lighting will not lead to a good swap, unless it has been very specifically matched for both your A and B side (although generally speaking, this is bad practice). You need to collect data from as many different sources as possible, with as many different angles, lighting conditions and expressions as you can, for both the A and B side.
  • You need to enable the "no-warp" option during training. "Warping" data is very important to build a robust model that can handle lots of conditions, however, to get a really good swap you need to turn this off towards the end of training. You can read more about it here

My word is final

Post Reply