Faceswap Forum

Honestly, I have never heard of that error. It does sound Windows specific/hardware related though, so you are probably best off with Google on that one,

This looks like the s3fd model file is corrupted. Navigate to the folder faceswap/.fs_cache and delete the file s3fd_keras_v2.h5 . This will cause the file to be re-downloaded. If you continue to have issues, you can manually download the file from: https://github.com/deepfakes-models/faceswap-model...

Do you have the correct installer? This is the Linux thread, you need the macOS version:
viewtopic.php?t=2748

Then it's as simple as entering your Downloads folder in terminal and entering:

Code: Select all

bash faceswap_setup_macos.sh

Most likely you are either continuing training the same model, in which case the mask you originally selected will be used (default is Extended), or you have started a new model but have neglected to select the BiSeNet-FP mask in training settings so the default is used (Extended). A screengrab woul...

However, during the extraction phase I checked "custom" masker for both. Custom masker doesn't really do anything. It just generates an empty mask for editing elsewhere. It doesn't hurt to have it, but it won't be helping you any. I thought it didn't matter for the training, and all I nee...

SilverFox wrote: ↑Wed Mar 27, 2024 1:00 pm
Nvidia-Smi still says i have Cuda 11.4 installed but i guess Cuda is backward compatible as FS installation have detected Cuda 10.2.

Nvidia-SMI reports the Cuda version that your GPU driver supports. Not the version that is installed. It is, however, not at all obvious that this is the case

You can't pass config items direct from the command line, no. You can, however, pass config file paths direct from the command line. So you can just create a different config file for each of your changes, and pass the relevant path in: -C CONFIGFILE, --configfile CONFIGFILE Optionally overide the s...

A screengrab would make this easier... But it should start resembling faces fairly quickly (within a save iteration or 2). If it isn't, then the model has collapsed and you'll most likely need to start again with a lower learning rate.

Hi, I'm a newbie in this so I'm confused as to why even after 35+ k only the 1st images of both sides are showing? I must admit that the next 2 on both sides are slowly showing some pixelated color but the rest is completely blank (grey). This sounds like one half of the model has collapsed... The ...

I can't say I have had this issue.

You could try just adjusting the weight of LPIPS down, rather than disabling it altogether.

app.php/rules#rule-4b.

You can re-use the encoder for any model with the load/freeze weights option. You can re-use any part of an existing model with these same options with the Phaze-A model. It is possible to load weights into any part of a new model for any faceswap model, but this functionality is not built in, and w...

hyln wrote: ↑Fri Mar 22, 2024 11:50 am
Once I start a training, I got below error from my crash report, how can I fix it

You input images on the B side has non faceswap extracted images in it. The training/timelapse images must all be faceswap extracted faces, and should be the same size.

Unfortunately there is not enough information in that error message to know what the issue is.

Most likely you are missing one of the pre-requisites

Not lost, but you will need to roll back. This error means that your model file is corrupted. Most likely training was interrupted during a save. You have 2 options, you can either restore from backup (you can use the model tool for this), or you can delete your model folder rename your latest snaps...

There was a bug which prevented the installer from running.

I have just pushed a fix for this, so please try running the installer again (no need to re-download it).

Ok, almost everything here could be improved and is covered in the training guide... in short though... "girl face b movie" folder: input b). I used the original trainer with bach size as 16 and 100000 interations, no folders for the timelapse, and no augments chosen. Original model is 64p...

Ok, this is odd that it worked before, but doesn't work now. I would normally suspect model corruption (when you crashed), but this is not a model corruption error. See if you can start a new model with these settings... If so, then most likely your model file is corrupted. If not, then this will pr...

You're going to need to be a lot more specific about the steps you have taken to get to this point. Most likely you have missed some crucial steps, have bad data, have a low res model or have not trained enough. If you haven't been following the guides. then follow the guides. They will help you a l...

Most likely you will need to delete your model, lower the learning rate (try 3.5e-5, if that doesn't work, then 1e-5) and start again.

Faceswap Forum

Search found 2666 matches

Re: Critical crash during extraction: KeyError: 'Unable to synchronously open object (free block size is zero?)'

Re: Critical crash during extraction

Re: [Guide] Linux Install Guide: Installer Method

Re: Masking for training?

Re: Masking for training?

Re: Feedback to an old issue.

Re: Config parameters from command line

Re: Training with Original trainer: after 35+ k iterations only the 1st A and 1st B images are showing

Re: Training with Original trainer: after 35+ k iterations only the 1st A and 1st B images are showing

Re: Teeth

Re: Is this training going well?

Re: A newbie question: Is it possible to partially re-use an already trained model if you decide to swap the person A?

Re: Training error

Re: [Guide] macOS Install Guide: Installer Method

Re: ERROR Caught exception in thread: '_training'

Re: I have been stuck in this position and cannot install successfully. How can I solve it?

Re: bugs on training

Re: Help! Unknown: CUDNN_STATUS_EXECUTION_FAILED Error out of the blue after PC crashed. Reinstall won't Fix

Re: bugs on training

Re: Preview only shows mask? Phaze-A, maskers: Bisect-Fp + Vgg-Clear + VggObstructed