Faceswap Forum

This is fine:
_extract_face called without a loaded image. Returning empty face.

For the other, I will need the crash report.

First question is, why do you think it's not using the GPU?

Also, check here:
app.php/faqpage#f0r3

I'd need to look at the model code, but IIRC I don't think so. I believe that the A and B side are structured differently.

Try the solutions proposed in this thread first and report back if you still have issues.

algeron wrote: ↑Wed Mar 31, 2021 6:33 am

May your losses never spike.

Honestly, that's not an answer we can really give.... it really is an experiment for the user. As you are aware, training models takes time, so we cannot test all (or any) settings. Generally higher = better, but that is a massive over-simplification and is only true to a point.

If you are needing to manually align 1000s of frames for a single video, then something doesn't sound right. Do you have image examples you can share?

Voice swapping is a difficult problem to solve, as evidenced by the lack of decent solutions. Ultimately there is a lot more nuance in voice than there are in images.

Unfortunately, at this moment in time, no there is no quick way to mask obstructions. It is a laborious face-by-face task....

It is most important for convert, although can help training too.

It is something on my road map to address.

Honestly? I'd need to investigate why that hard coded value was put in in the first place. My preference would just be to remove it altogether, as I am not particularly a fan of setting environment variables inside applications.

The FAN model file has corrupted. Most likely during download....
Delete the file:

faceswap/plugins/extract/align/.cache/face-alignment-network_2d4_keras_v2.h5

and try again

I would say that editing the code directly is rarely the best idea, as it can prevent Faceswap from updating.

Go into Training Settings and try reducing the Convert Batchsize

Honestly? It's entirely up to you for whichever works best for you workflow wise.

Personally I tend to stick to separate sources, but there is no reason not to compile all your sources together.

Sure it can, but it's going to require work on your part, and is not a feature we are likely to ever build in.

Ultimately, it is a masking problem. You have access to the 68 point face landmarks, so you can create "sub-masks" for any area of the face from that, and use those for conversion.

Yeah. It's a GUI bug. Doesn't impact training, just stops the graph updating for that session.

I'll fix it one day.

That has nothing to do with merging alignments.

Merging alignments file was an old training process. You're trying to convert.