Faceswap Forum

NB: This guide was correct at time of writing, but things do change. I will try to keep it updated. Last edited: 15 Apr 2024 --- Contents Contents Introduction Why Extract? The Alignments File Extracting Extract Configuration Settings Extract Setup Sorting Clean the Alignments File Manually Fix Alig...

You are pointing convert at the wrong thing.

The input should be the video you want to convert NOT your faces folder

This has been patched in the latest version of the Faceswap code. It basically occurs because a library we rely on looks for Nvidia drivers where Nvidia puts them and not where Windows puts them. If people are still hitting this issue, then do one of the following: From the GUI: run "Tools menu...

You don't need to install the manual way.

Installing with the installer will be fine to follow these instructions

That's pretty much exactly right.... You can either point the TimelapseA/B at your input folders, in which case it will take the first (14?) images from that folder and create a timelapse, or you can put selected photos from your trainset into another folder purely for the timelapse. At every save i...

Installing Faceswap on Windows is a breeze. The windows installer installs everything you need except for your Graphics drivers. If you are using a Graphics card (which is highly recommended. Faceswapping on CPU is incredibly slow), then make sure your drivers are up to date. Download the Faceswap I...

Not easily, no, given the sheer amount of data that needs to be transferred. The slow going is one of the more frustrating parts of it, and is what makes model development take so long. If you have to wait 12-48 hours to find out if the model you are developing has improved at all it somewhat burns ...

I would. Higher batch sizes are averaging over a larger dataset, so may normalize out little details. There is still some debate over what is best, but generally, if I am training a model where I can have a high batch size, I will normally start on a high batch size, then reduce it once the face sta...

Welcome to the Forum! From what you have said, you are probably already aware, but the absolutely most important thing is quality of data. Unfortunately YouTube isn't a great source of data as they perform quite aggressive compression on their video files. If you can get your target from other HD So...

We have found a potential solution to this issue, but need to test it works before pushing to the main repo. If you are having this issue, please try the following: Open up an Anaconda Prompt: Start > Anaconda Prompt Then execute the following commands: conda activate faceswap pip uninstall nvidia-m...

We are looking into this. The problem is upstream of us with how the pynvml module (module for reading Nvidia driver information) gets its information. It expects it the information to be in the Nvidia location, not the Windows location. If you can get the Standard drivers installed, that will defin...

Thanks for the update. This is useful information. There is currently an issue where if Windows Update/Store installs your Nvidia drivers, then FaceSwap can't read the information. Extract will fail in this situation as we cannot dynamically allocate VRAM. If you enable "single process" mo...

We would need the full crash_report to be able to diagnose this (from inside the faceswap folder)

Also I don't know what FaceRipper is..... Assuming it's a 3rd party app, the ONLY supported way of generating facesets is through FaceSwap Extract process.

That isn't normal, no. In theory if it can't find your GPU it shouldn't be able to use it (for extraction at least). Normally I'd try to diagnose this issue, but if it works, then I'd leave it for now until/unless you have problems. One thing though, could you tell me if nvidia-smi.exe exists in eit...

This has happened to me before. I don't like it when I see it, but it should be ok.

To be honest, if it's early in the train I tend to kill my model and start again, because I'm super paranoid.

Your driver is still too old. From Nvidia website: CUDA 10.1 (10.1.105) >= 418.39 CUDA 10.0 (10.0.130) >= 410.48 You are now on version 399.24... Closer but still not there. The latest TITAN X (Pascal) Driver available on Nvidia's website is version 431.36 Make sure you reboot after installing the d...

The most likely issue for this is that you have Windows drivers installed through Windows Update/Windows Store. This is fine for gaming, but unfortunately presents problems for Machine Learning. Unfortunately Windows does not make it easy to remove this driver and not have it re-install itself strai...

First load can take several minutes as Cuda needs to compile a load of stuff. It may time out. If it hasn't after about 10 minutes, kill it and run again.

It will be fine every time after.

You need to update your graphics driver. gpu_driver: 397.64 This is insufficient for Cuda 10. From Nvidia website: CUDA 10.1 (10.1.105) >= 418.39 CUDA 10.0 (10.0.130) >= 410.48 Get the latest Driver available on Nvidia's website . Make sure you reboot after installing the drivers Thanks

Hi Jakeeye

Please post the contents of the crash log listed:

Code: Select all

C:\Users\Test Machine\faceswap\crash_report.2019.07.15.133351430277.log

Faceswap Forum

Search found 2681 matches

[Guide] Extraction - A Workflow

Re: Convert Can't find video/Only swaps faces

Re: "NVML Shared Library Not Found" with new drivers.

Re: "NVML Shared Library Not Found" with new drivers.

Re: Timelapse

[Guide] Windows Install Guide: Installer Method

Re: Optimum Training Settings

Re: Optimum Training Settings

Re: Optimum Training Settings

Re: "NVML Shared Library Not Found" with new drivers.

Re: Is it necessary detecting GPU&driver for use?

Re: Is it necessary detecting GPU&driver for use?

Re: Alignment file

Re: Is it necessary detecting GPU&driver for use?

Re: Loss briefly spiked, then recovered. What happened?

Re: Extraction hangs on "Starting, this may take a while..."

Re: "NVML Shared Library Not Found" with new drivers.

Re: Extraction hangs on "Starting, this may take a while..."

Re: Extraction hangs on "Starting, this may take a while..."

Re: Extraction hangs on "Starting, this may take a while..."