Faceswap Forum

It's possible to do any of the Faceswap processes on Google Colab. I don't use it, personally, so can't help you with how, but it shouldn't be too involved.

ianstephens wrote: ↑Mon Jul 12, 2021 8:31 pm

Quick question @torzdf -

Did you use "no warp" at the end of training for this video? Or was it simply a run of _2M iterations with the StoJo preset model?

Yes. Can't remember when I disabled. Probably about halfway through

ianstephens wrote: ↑Tue Jul 06, 2021 1:52 pm

Is this simple change below all it takes to train at 384px for example (or is there more to it)?

Short answer. You could just do that, but there's more to it.

Long answer: A lot of maths.... I will come back and articulate at some point in the (hopefully) not too distant future.

That speed is about correct for StoJo. It is a heavy and complex model.

Roudrunner_404 wrote: ↑Thu Jul 08, 2021 1:37 pm

Ok so. I might not be that smart but. Must I swap face in the video I used for training?

No. It's best to follow the guides to understand how it all works (it's easier than me just re-explaining it all here)

The GTX 710 is too old to use the latest Faceswap version (requires Compute Capability 3.5+). Also, 2GB means you may not be able to do very much. You can try V1 of Faceswap though, which should work on your card:

https://github.com/deepfakes/faceswap/r ... tag/v1.0.0

Just use the preview tool to adjust the size of the mask to exclude the eyebrows.

babala wrote: ↑Sun Jul 11, 2021 10:22 pm

so I my 3080 start running now.

with batch size 4 and 12.8 EGs/sec. and batch size 5 also working but 1 EGs/sec more so...

is this normal speed for Phaze-A ?

That very much depends on the settings you choose.

FWIW convert is not particularly well optimized.

Either way, It should never use all of your RAM. It's specifically built to try not to use it by only holding onto those frames that it is processing at any given time.

Moved to general, as I'm not sure what you're asking for here.

How much GPU/CPU to use for what?

I will need to look into + test this. My initial assumption would be memory copies though

If you can't strip the metadata then use the EFFMPEG tool to split the video into separate frames and run convert on that (Tools > Effmpeg)

[mention]bryanlyon[/mention] is best with hardware advice, and [mention]deephomage[/mention] or [mention]abigflea[/mention] are better with multi-gpu setups.

However, mixing between generations is possible, but is not ideal. You will be limited by the speed and vram of the older GPU

It would be great to have something like this "automagically" included in Faceswap, but I can't see it being anything I'll be looking into any time soon.

Ultimately (for the time being at least) these kind of fixes are best done with post-editing tools.

re-run the installer. Point the installer to your existing install of miniconda when asked.

If it still fails, then just manually install faceswap.

No, it's the mask blending. It's all explained in there. I'm not going to repeat the information in the guide. If you have specific issues, then raise them.

Ultimately the preview tool shows you how it will output the final swap.