Faceswap Forum

The data is viewable. You can use the manual tool to view the alignments. The only part of the alignments.fsa file that isn't yet in the manual tool is the mask, which will be added in the new version that is currently in the works.

We do not expose the fsa file since it's not final. That said, the intended way of manipulating the FSA is through the alignments tool (Including the manual tool). You don't actually need to change the filename in the alignments.fsa since we use the hash of the image to find the matching alignment. ...

Tensorcore support is on our list of future enhancements. However, in order to add tensorcore support we need to replace a good chunk of code. Part of the problem is that the version of Keras we use does not support Tensorcores, but we can't change to the newer version without removing AMD support. ...

Most cards should be thermally safe at their maximum operation speed. They should be okay indefinitely. That said, if you can add some cooling to reduce the temperature it's not a bad idea. If your card hovers in the 90c range you might want to underclock it to keep it cooler. There shouldn't be any...

Batch size is the first one to try. If that's not enough you can go in to the model settings to reduce quality or you can enable memory options while training.

Ultimately you have 6gb of vram so can use most lighter models without too much trouble but will struggle with the larger models.

This really isn't much information to go on. Are you failing to see them in Extract or Convert or is this during Training? If it's Extract or Train, can you detail where in the guide you fail to find them? Extract: https://forum.faceswap.dev/viewtopic.php?f=5&t=27 Train: https://forum.faceswap.d...

There are other ways to unwarp, that's just one tutorial. But you will have to unwarp it before you can convert.

You first need to unwarp the VR video. See for example then only after you unwarp it can you convert it. Then you'll want to rewarp it back so it looks correct in VR.

This is a relatively common problem. Use the restore tool to load the backup and continue from the last good result.

Right now, if no masks work for you there isn't much you can do about it. Torzdf does have an updated manual tool in the works that will allow you to manually mask the face, but right now it is not yet available.

This is often masking a memory error. If you've already turned on Allow Growth in the Extract plugins, you may try turning down the BatchSize in the Settings/Extract Plugins/Mask/Unet DFL.

viewtopic.php?f=6&t=146
This is the best source of information on this. Honestly, much more than what this guide shows is overthinking things. Just go for the largest Batch Size you can without turning on any memory hacks (as those slow down training for Vram).

Training speed is not just iterations. It's actually best to use the number of images in a time period. So Batch Size * Iterations is a better calculation So 50 * 240 = 12,000 images/hour 30 * 500 = 15,000 images/hour 6 * 900 = 5,400 images/hour (I however, believe you've likely mistaken the speeds ...

Not really, no. Storage is much slower than the vtam on board the gpu and relying on it as vram replacement is not viable. Also, the images must be augmented so even streaming the raw images isn't viable. Further, consumer pcs don't have separate pci-e switches that allow the gpu to directly read fr...

This is a weird error that we've seen once before. See https://github.com/deepfakes/faceswap/issues/954 Unfortunately, none of the developers have been able to reproduce it. We are trying to look into it, but it may simply be a corrupted install. That error code is not coming from our application, b...

Please post your crash log (if present). It'll be in the faceswap folder named "crash_report[date].[longnumber].log . If not, post your system info: GUI Users: Go to Help -> Output system information CLI Users: From inside your virtual environment, inside your faceswap folder, run: python -c &q...

Any time there is a mark you want to preserve on one side of the face you should disable the flip option throughout the entire training process. If you do this please be aware that you'll want to include a significantly larger dataset to ensure the quality of the results.

It's not critical. You could certainly get away without upgrading the CPU, but you WILL see better speeds if you upgrade it later. Might be worth scheduling it sometime down the line.

Yes. a 2060 super would let you turn off a lot of the memory preservation you're currently using which is honestly the thing most slowing you down with your 960. I'm not going to promise double the speed, but you'll see some strong speed improvements. The only problem is that with a 2060 super, your...

I've never used it. They look fairly legit but you can never be sure. Maybe you'd rather try the free tier of Paperspace https://docs.paperspace.com/gradient/in ... -instances ?

Faceswap Forum

Search found 790 matches

Re: viewing/modifying alignments.fsa?

Re: viewing/modifying alignments.fsa?

Re: RTX Tensor Cores in Faceswap

Re: Has deepfaking for long periods caused anyone long-term hardware issues?

Re: New computer build issues

Re: Not seeing the images on my computer when I try to pick a image

Re: Has anyone made a VR deepfake before? Is it easy?

Re: Has anyone made a VR deepfake before? Is it easy?

Re: After training for 24+ hours, mask turns solid black, and lost A and lost B is nan

Re: Creating masks for heavily obstructed faces

Re: Error when masking with Unet post extraction

Re: Speed/Quality and Batch size

Re: Speed/Quality and Batch size

Re: Nvidia recently posted information saying that NVME could be used as

Re: Failed and return code: 3221225477

Re: Failed and return code: 3221225477

Re: No flip for specific faces

Re: Hardware best practices

Re: Hardware best practices

Re: free genesiscloud gpus any good?