Faceswap Forum

It took me a while to understand Lpips in usage because strange and ugly stuff seems to happen always.
I went on with experimenting because my normal ms-ssim seemed to be not very effective in training with clipV

So i did Logcosch + Lpips vgg16 and i was amazed.
The first 3000-5000 its you only see very ugly faces and you wonder if it will every succeed.
at 10000 its you see sharp but somewhat strange faces.
and then it very quickly gets very good. You just have to ignore the beginning strangeness.

For now this experience is only with clip, but with this loss function combo the results are way better with a very reduced training time then using MS-SSIM loss function.
When combining MS-SSIM with Lpips vgg16 also gives much slower training results.
Vgg is way more effective then squeeze

The level of detail i get with clipv on this loss function way exceeds what i ever got with other loss functions.

Thanks for these updates!

the trick is just ignore the ugly strangeness for long enough en then it gets pretty

FWIW, vgg16 is vastly superior to the other flavours of LPIPS, but is more of a VRAM hog.

Training very high resolution models, I don't get artefacting at all from it

Ryzen1988 wrote: ↑Wed Oct 11, 2023 11:22 am

It took me a while to understand Lpips in usage because strange and ugly stuff seems to happen always.
I went on with experimenting because my normal ms-ssim seemed to be not very effective in training with clipV

So i did Logcosch + Lpips vgg16 and i was amazed.
The first 3000-5000 its you only see very ugly faces and you wonder if it will every succeed.
at 10000 its you see sharp but somewhat strange faces.
and then it very quickly gets very good. You just have to ignore the beginning strangeness.

For now this experience is only with clip, but with this loss function combo the results are way better with a very reduced training time then using MS-SSIM loss function.
When combining MS-SSIM with Lpips vgg16 also gives much slower training results.
Vgg is way more effective then squeeze

The level of detail i get with clipv on this loss function way exceeds what i ever got with other loss functions.

I'm a newbie, I would like to know what the specific configuration weights of the loss function you use are。Loss Function Loss Function2 Loss Function3 Loss Function4，Sorry for my poor English, I use machine translation。Thank you so much