Faceswap Forum

The easiest way to see it is visually. Look at the "red" area in the training previews. These are masked out. Features are badly learned in the masked out area (this is the point of masking without 'learn mask enabled', it tells the NN which parts of the image it is interested in, and whic...

Thank you for your advise , Would you please suggest some setting about 1080p video for using V2 with rtx 3080 n 3090 ? because for now , v2-s with stojo present , 1080p video , some close-up shot the face go blur , but v2-l with stojo present much better . suggestion like : extraction px phaze-A o...

Ok, good to know. Thanks. I will look at the potential for choosing to put that on cpu.

Looks like model corruption to me.

You'd need to try rolling back 50k or so, lowering learning rate a bit and continuing.

Just an update. I'm noticing that there is a much longer delay between iterations compared with, for example, the 256 StoJo model. The GPU is not used to its full potential. For example, this is a graph for I believe the slowdown is caused by the larger amount of data (larger image sizes - which ar...

Removing the bug tag from this as -d, --distributed is deprecated in favour of -D, --distribution-strategy

No. It is purely a numbers thing. I doubt I would implement anything like this, because if you're at the point of reviewing every single frame, then you might as well review every single face. At which point, you're manually going through everything anyway, so could build your training set that way.

Which mask were you using? If landmarks based mask, then the GPU isn't used at all. The mask is generated from landmarks.

If it was an NN based mask, it would seem unlikely. However, let me know which one, because if it is as fast on CPU, then that is something I would want to look at.

Yes, there are huge benefits for multiple reasons. Off the top of my head: 1) Landmarks based masks are only as good as the landmarks. It really requires very precise landmark alignments for the mask to be effective. For face alignment, only the core landmarks are used (all landmarks, excluding the ...

Gradient clipping is a mechanism to help prevent exploding/vanishing gradients (that is numbers that go to +/- infinity or to 0). Both of these will cause a model to NaN (Mixed Precision is more prone to this, as infinity in limited precision space is a smaller number than infinity in full precision...

Protip: Don't report the forum owner for spam.

It is in the convert guide. Literally covered in the first section. Also this:
viewtopic.php?t=2090

Not directly. If you select the "summary" option, it will output the summary of the configured settings, not the stored model (which can be different). You can get the summary output though by enabling "verbose" log level and not selecting "summary". This will start tra...

I'm not really sure what you mean by the first part of the question... You can use the mask tool to output a visual representation of the masks stored. EEN doesn't pull out a random choice, it extracts every N frames (so if you set EEN as 10, it will extract faces from every 10th frame, assuming tha...

This is an error in your local configuration. First try this: https://forum.faceswap.dev/app.php/faqpage#f1r1 If that doesn't work, then the issue is with your system: https://www.google.com/search?channel=fs&client=ubuntu&q=ProxyError%3A+Conda+cannot+proceed+due+to+an+error+in+your+proxy+co...

Yes. It was the same issue for all Windows versions. An update was pushed yesterday which broke the setup script.

A fix has been pushed today.

Re-run the installer.

Noted. Extract guide updated.

I have pushed an update which should fix this. Please re-run the installer

There's currently a bug in the installer for Windows. I'm currently looking at a fix.

No, I would go higher. I have the maths somewhere.... Basically, if you are training on Face Centering at 100% you'd want to multiply the model input size by 1,33% (this is how much extra space is padded on to extracted images for head centering). So 1024 (model output size) * 1.333 = 1366px (the si...

When running the installer select the "Show Details" box during installation. When the installer fails, paste the output of the details box here and we'll be able to see why installation failed.

Faceswap Forum

Search found 1838 matches

Re: Clarificaton on Training options: Mask selection

Re: [Guide] Introducing - Phaze-A

Re: Masking with CPU

Re: wired highlight patches

Re: Potential VRAM Saving techniques

Re: Bug: ValueError: Please use `tf.keras.losses.Reduction.SUM` or `tf.keras.losses.Reduction.NONE`

Re: saving individual frames from manual

Re: Masking with CPU

Re: Clarificaton on Training options: Mask selection

Re: AutoClip: Any Feedback From Users?

Re: How do I change the face of only one of two people in one picture?

Re: model architecture

Re: Faces for Training Question

Re: Installation error Creating Conda Virtual Environment: ProxyError: Conda cannot proceed due to an error in your prox

Re: Faceswap + Windows 11 = Nope!

Re: Delete/copy/paste/many - face alignments

Re: Faceswap + Windows 11 = Nope!

Re: Faceswap + Windows 11 = Nope!

Re: Potential VRAM Saving techniques

Re: Windows Installer error: “Some applications failed to install.Process Aborted.Check Details.”