Faceswap Forum

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.

DId you close and re-open the terminal after installing Faceswap? If not, you need to....

Then it would be:

conda activate faceswap
cd faceswap
python faceswap.py -h

If the conda command is still not found, you may have to install miniconda3 yourself manually.

What do you mean it doesn't run? Do you get any error message output when you try to launch Faceswap?

You can do this with the Preview tool:

viewtopic.php?f=7&t=1083#Preview-Tool

Yeah, I think that model has collapsed. You can try rolling back to an earlier snapshot and lowering the learning rate.

You should look at the graphs in the analysis tab as it will hopefully give you an idea of when it failed and if it was still learning anything at that time.

I honestly don't know the answer to this question. Every time I try to give one, I see an argument for doing the opposite. The best I can offer is "experiment and see what happens".

I wish I could give you something more definitive.