Faceswap Forum

For going out of frame faces, I find a couple of things work ok for me: The alignments are manually fixed. These don't need to be perfect. I tend to just copy from the last frame, then in Extract Box mode (green box), I move the box until the visible landmarks lineup close enough Some of these 'goin...

This is just a GUI issue, not showing the preview about it.

Specifically there is a permission issue on your machine accessing the preview file.

Don't worry about it. Whilst you can't see the preview, it won't impact the ability to convert.

Hi I need help with this installation process... I tried installing the Faceswap 3 on my kali linux and this is what am getting (base) ┌──(tejiri㉿kali)-[~] └─$ git clone https://github.com/deepfakes/faceswap.git fs3 Cloning into 'fs3'... remote: Enumerating objects: 14675, done. remote: Counting ob...

@ianstephens Thanks for testing. Unfortunately I have been very busy of late, so not much time for development.

I have made a note of your feedback and will investigate as soon as I get an opportunity.

I'm don't know anything, offhand, that will do this, but Faceswap will not be suitable as the style of the swapped face will be very real.

This is not an issue I have seen, but it sounds like the model has collapsed.

Roll back _50k iterations and lower the learning rate

On the installation page it says CUDA 3.5 or higher will support. But on the release page it is written CUDA 9+ is required. In the forum discussions I found members are using 10XX, 20XX, 30XX or 40XX which are most likely CUDA 8.X version supported. I am not sure if I am getting it correct but wil...

Loading... Setting Faceswap backend to APPLE_SILICON Metal device set to: Apple M1 Max systemMemory: 32.00 GB maxCacheSize: 10.67 GB 09/13/2024 01:24:12 INFO Log level set to: INFO 09/13/2024 01:24:13 INFO Reading alignments from: '/Users/nadirtsemach/faceswap/workflow/111_alignments.fsa' 09/13/202...

This is likely a bug in the code somewhere.

Sadly, it will be hard to find without the original data.

If you can provide: The video that you are converting + the alignments file, I can look into this (You are welcome to send me a link via private message)

Faceswap would definitely work for your usecase, but I'm not entirely convinced it is the best way to go, for a few reasons: The problems are there are a lot of subjects to alter, several shots contain several faces. They sometimes turn around, move quickly, wear glasses, have objects passing in fro...

A screen grab of the preview window would be useful...

However, this sounds almost definitely that you selected the extended/components mask when starting training.

The selected mask is 'locked' to the model, so changing it after the model has started training will have no effect.

Welcome back :) That was probably the DLIB extractor which, yes, has been completely removed from the project (due to being inferior to current offerings, and constantly causing issues for end users as it needed to be compiled to use the GPU). The convert guide is kept up to date, and faceswap has a...

Unfortunately not directly, as this is 'locked' to the model.

You could edit the model's statefile, although this is unsupported, and I'm not sure there is any value in switching the loss in this way.

I will look into it when I have time (sorry for slow response, I'm very busy at the moment!)

Ok, a couple of things... The log file you gave me does not show a not C-contiguous error. It shows a missing mask error, so the solution to this problem may not be the solution to the initial problem The reason why the first frame is failing is precisely because you edited the first frame. Any and ...

I don't think I've heard of anyone training it to completion, for the reasons you state. It takes a very long time.

Would be interested to know how you get on.

I will also need the source video that this alignments file relates to, to be able to diagnose this, I'm afraid.

Thank you for confirming

I'm afraid not. It is not an issue that has impacted me for a long time. As I said, it is likely to be data related, so make sure you are well covered off on both sides for the scenes you are struggling with.

Faceswap Forum

Search found 2739 matches

Re: Shake of a half-visible face

Re: convert problem

Re: Faceswap 3 open for testing

Re: Faceswap 3 open for testing

Re: Using converting data for training

Re: Cartoon face swaps with real faces

Re: Villian Training always reaches a point where the output just becomes white face

Re: New to swap. Please help me with hardware questions

Re: conversion problem

Re: [Guide] A Rough Guide to Converting

Re: Questions about a project.

Re: Training is not including the entire face

Re: Does the old "cnn" extractor still exist? Need help with updating commands from a very old version of this program!

Re: Can Penalized Mask Loss be changed in the middle of training?

Re: AV1 Encoding

Re: Conversion Error: ndarray is not C-contiguous

Re: [Guide] Introducing - Phaze-A

Re: Conversion Error: ndarray is not C-contiguous

Re: Faceswap 3 open for testing

Re: How to correct the dreaded micro-jitter?