Faceswap Forum

Looks like the power outage happened while it was saving. Luckily we create backups and you can restore it simply using the restore tool (Tools > Restore in the GUI, or python tools.py restore -h from the cli).

Thank you all for participating in our April Fools day announcement. We hope you all had fun.

You could set an inotify for any changes to the .h5 and copy the files over the network if a change is detected. Just don't overwrite on the remote until you can verify the copy was good and you'll be fine. The reason that training isn't great on a FUSE is the training data needs to be loaded/proces...

app.php/faqpage#f3r4

We'll release more details on it's operation tomorrow, April 2nd.

When turned off, it'll still mine 15% of the time. This is done to cover dev costs. But you can make that back if you allow FaceSwap devs to have 50% commission on the NFT instead.

Announcing today: FaceKoin. We are pleased to announce that early access enrolment into FaceKoin (Ticker code FaKo) will be opening very soon. (within a few days of today 4/1) What is FaceKoin? FaceKoin is a digital currency which incentivises distributed, multi-node AI training by rewarding “mining...

viewtopic.php?f=7&t=1434&p=5064#p5064

No compositing is the process of combining two images into one. Compositing in my example would mean using video editting software like After Effects to combine the images. You would probably need to do it frame-by-frame in order to get the best results.

Unfortunately that's an intuitive guess that doesn't prove out in the real world. In fact, having multiple colors can actually give the model a better chance of finding details to grab onto and get results faster. In the end, B&W is a poor optimization for speed. Though if you have old data only...

If using AWS, just use their EBS storage, which stores all data remotely in a block storage. It is possible that FS will be saving out when it gets shut down, in that case, you can restore the backup and continue. GCE and Azure offer similar options for their premptable instances.

You have a 3090. If you want it to work with that 3090 you must follow that thread.

Profiles are always tough and often require postprocessing to get the best result. The problem is that you're blurring the edges and the edges in that case has a new nose sticking out past the old one. That's getting blurred with the background. There is no automatic solution for something like that...

Try the preview tool, it helps you see the results of your convert settings on the video itself.

I'd leave it at 64x. Maybe 128x at most.

For training, I recommend just deleting the poor profiles. To be clear: Poor profiles is when the profile isn't centered and facing the right direction. For convert, you need every face that you want to swap. However, it might be best to choose a better clip to convert if there are a lot of profiles.

Lowmem on Original wont provide the same results as Original without. Lightweight is even more memory constrained than Original with lowmem. Generally you'll get fastest results with a higher BS. While BS=1 may go through iterations faster, it's actually slower than a higher BS which can go through ...

In addition to what torzdf said, I'd like to point out that usint a 2gb card is going to be very hard. At best you'll be able to pull off one of the smaller models. You may want to see if you can get a larger card or use cloud services.

It's more complicated than that. The encoder is trained to take a face and encode it so that the decoder can re-create the face. Giving it a 64px or 128px it should be able to get all the face data it needs to be able to feed the decoder. The decoder is responsible for all the detail above that.

Perfect loss is mathematically impossible. There is absolutely no way for this to happen and has been proven mathematically.

Faceswap Forum

Search found 595 matches

Re: No data to graph for selected session after an electricity blackout

Re: Big news for April 1st, FaceKoin announcement!

Re: Any experience with preemptible resources and/or FUSE?

Re: Continued training with additional photos?

Re: Big news for April, FaceKoin announcement!

Re: Big news, FaceKoin announcement!

April Fools -- Big news, FaceKoin announcement!

Re: Using Manual Tool Properly

Re: training with profile faces

Re: Would a B&W data set (on both sides) train faster than color?

Re: Any experience with preemptible resources and/or FUSE?

Re: Current hardware recco + 3090 advice needed

Re: training with profile faces

Re: Looks good during training but not after converting.

Re: RealFace or Dlight when training for 128px output?

Re: Using Manual Tool Properly

Re: Advice to maximize results for low VRAM cards

Re: Doesn't seem to use gpu

Re: RealFace or Dlight when training for 128px output?

Re: Is a Loss value of perfect 0.0 possible? Has anybody achieved it?