Search found 2654 matches

by torzdf
Tue Apr 16, 2024 5:47 pm
Forum: Convert Support
Topic: Alignment files Bug
Replies: 1
Views: 134

Re: Alignment files Bug

Hmm, I've not hit either of these issues.

I will investigate tomorrow, but if you could provide reproducible steps, it would be appreciated.

by torzdf
Tue Apr 16, 2024 5:45 pm
Forum: Installation Support
Topic: Tensorflow library compiled to use AVX Instructions
Replies: 2
Views: 37

Re: Tensorflow library compiled to use AVX Instructions

Unfortunately Tensorflow requires AVX support from your CPU to be able to be used. Your CPU does not appear to have this. The only way around this is to compile Tensorflow 2.10 yourself without AVX support (or look for a custom Tensorflow 2.10 wheel that has been compiled without AVX support). I wou...
by torzdf
Sat Apr 13, 2024 10:57 am
Forum: General Discussion
Topic: Have you considered using FaceSwapLab in this UI/App?
Replies: 1
Views: 684

Re: Have you considered using FaceSwapLab in this UI/App?

I'll be honest, I haven't looked at it, but I assume (being SD based), it is single image onlly?

Either way, its something I'm unlikely to do as the architectures are very different.

by torzdf
Sat Apr 13, 2024 10:55 am
Forum: Installation Support
Topic: Install aborted: fatal: fetch-pack: invalid index-pack output. Error Downloading Faceswap
Replies: 1
Views: 128

Re: Install aborted: fatal: fetch-pack: invalid index-pack output. Error Downloading Faceswap

This is a network error when downloading Faceswap from Git. It may be temporary or your network connection may be unstable.

You can try again to see if it was temporary, or try with a better network connection

by torzdf
Wed Apr 10, 2024 4:38 pm
Forum: Extract Discussion
Topic: Browsing datasets with masks
Replies: 6
Views: 435

Re: Browsing datasets with masks

Masks in the png header are zlib compressed. Thank you this is helpful, maybe I can extract the mask this way and make a quick and dirty faceset browser. I know you're extremely busy so it would be low on your priority list to ask for a new Browse panel :lol: The manual tool will never be adapted t...
by torzdf
Wed Apr 10, 2024 4:35 pm
Forum: Extract Discussion
Topic: Browsing datasets with masks
Replies: 6
Views: 435

Re: Browsing datasets with masks

Thanks torzdf, that's what I tried but always get this when I select the faces folder: 04/10/2024 11:30:57 ERROR The input folder '\\blahblah\extracted512' contains extracted faces. 04/10/2024 11:30:57 ERROR The Manual Tool works with source frames or a video file, not extracted faces. Please updat...
by torzdf
Wed Apr 10, 2024 10:10 am
Forum: Installation Support
Topic: [Guide] macOS Install Guide: Installer Method
Replies: 35
Views: 91395

Re: [Guide] macOS Install Guide: Installer Method

As stated above... there is not enough information in that error message.

See if you can do the cli version of this:
app.php/rules#rule-4a

by torzdf
Wed Apr 10, 2024 10:07 am
Forum: Extract Discussion
Topic: Browsing datasets with masks
Replies: 6
Views: 435

Re: Browsing datasets with masks

1) How can we browse our dataset folder in a similar fashion as the training previews, i.e. with the red mask overlaid on the image, and Manual tool. Lets you view and edit masks. 2) If I had to, how can I decode the mask code inside the PNG to make my own viewer in Python etc? You can export masks...
by torzdf
Sun Apr 07, 2024 12:32 pm
Forum: Extract Support
Topic: Critical crash during extraction: KeyError: 'Unable to synchronously open object (free block size is zero?)'
Replies: 3
Views: 267

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

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,

by torzdf
Fri Apr 05, 2024 11:23 am
Forum: Extract Support
Topic: Critical crash during extraction: KeyError: 'Unable to synchronously open object (free block size is zero?)'
Replies: 3
Views: 267

Re: Critical crash during extraction

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...
by torzdf
Mon Apr 01, 2024 11:22 am
Forum: Installation Support
Topic: [Guide] Linux Install Guide: Installer Method
Replies: 28
Views: 242653

Re: [Guide] Linux Install Guide: Installer Method

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
by torzdf
Sun Mar 31, 2024 6:22 pm
Forum: Training Discussion
Topic: Masking for training?
Replies: 4
Views: 349

Re: Masking for training?

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...
by torzdf
Sun Mar 31, 2024 11:28 am
Forum: Training Discussion
Topic: Masking for training?
Replies: 4
Views: 349

Re: Masking for training?

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...
by torzdf
Wed Mar 27, 2024 2:05 pm
Forum: Installation Support
Topic: Feedback to an old issue.
Replies: 2
Views: 332

Re: Feedback to an old issue.

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

by torzdf
Tue Mar 26, 2024 2:22 pm
Forum: Extract Support
Topic: Config parameters from command line
Replies: 2
Views: 301

Re: Config parameters from command line

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...
by torzdf
Tue Mar 26, 2024 2:20 pm
Forum: Training Support
Topic: Training with Original trainer: after 35+ k iterations only the 1st A and 1st B images are showing
Replies: 3
Views: 424

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

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.

by torzdf
Sun Mar 24, 2024 7:54 pm
Forum: Training Support
Topic: Training with Original trainer: after 35+ k iterations only the 1st A and 1st B images are showing
Replies: 3
Views: 424

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

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 ...
by torzdf
Sun Mar 24, 2024 7:51 pm
Forum: Training Discussion
Topic: Teeth
Replies: 5
Views: 844

Re: Teeth

I can't say I have had this issue.

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

by torzdf
Sun Mar 24, 2024 7:50 pm
Forum: Training Support
Topic: A newbie question: Is it possible to partially re-use an already trained model if you decide to swap the person A?
Replies: 1
Views: 222

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

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...