Search found 1434 matches

by torzdf
Tue Aug 03, 2021 10:34 am
Forum: Convert Support
Topic: Transparancy dissapears running Ffmpeg
Replies: 7
Views: 109

Re: Transparancy dissapears running Ffmpeg

Ok, I have not done this, so I can't give you the exact steps. But... the problem you need to solve is you have an image sequence in RGBA format. The mask is in the alpha channel..... You need to follow one of 2 approaches, I cannot tell you which is best, or which is easiest, as I do not know. 1) A...
by torzdf
Mon Aug 02, 2021 9:57 am
Forum: Convert Support
Topic: Transparancy dissapears running Ffmpeg
Replies: 7
Views: 109

Re: Transparancy dissapears running Ffmpeg

The images are saved as 4 channel RGBA pngs when enabling draw transparent. This can be carried through to video by changing the pixel format in ffmpeg (this is a command line thing in the original application, not something available in faceswap. RGBA video is so niche that it is not worth looking ...
by torzdf
Sun Aug 01, 2021 10:01 am
Forum: Extract Discussion
Topic: [Guide] Extraction - A Workflow
Replies: 64
Views: 341277

Re: [Guide] Extraction - A Workflow

Are you definitely inside the faceswap environment? Pathlib is an explicit pre-requisite

by torzdf
Sat Jul 31, 2021 2:07 pm
Forum: Training Support
Topic: Occur error when click 'Graphs' icon for selected session.
Replies: 1
Views: 1401

Re: Occur error when click 'Graphs' icon for selected session.

Not a bug. It looks like you are using a more recent version of matplotlib than is in our requirements. This is a known issue in versions of matplotlib>=3.3.0. Downgrade your matplotlib

by torzdf
Sat Jul 31, 2021 9:28 am
Forum: Convert Discussion
Topic: Possible to have only the new face, without the head?
Replies: 8
Views: 470

Re: Possible to have only the new face, without the head?

Yes. Use the openCV or Pillow writer with the "draw-transparent" plugin configuration setting.

by torzdf
Wed Jul 28, 2021 9:43 am
Forum: Extract Discussion
Topic: How important is it for the jawline and eyebrows to be perfect, assuming other landmarks are good?
Replies: 3
Views: 1554

Re: How important is it for the jawline and eyebrows to be perfect, assuming other landmarks are good?

It's funny though, even with a well-defined chin, videos converted with extended tend to cut off the bottom just below the mouth, rather than including the full contour of the chin. That will depend on the centering used for training, the coverage used, and how much erosion is applied to the mask a...
by torzdf
Wed Jul 28, 2021 9:41 am
Forum: Cloud Discussion
Topic: termios "inappropriate ioctl" error when running in startup-script
Replies: 2
Views: 884

Re: termios "inappropriate ioctl" error when running in startup-script

You are correct that a terminal needs to be present to monitor for keypresses. If you don't mind dabbling in code you could probably script that stuff out from here: https://github.com/deepfakes/faceswap/blob/master/lib/keypress.py Otherwise, disabling the terminal monitor is not something I'm likel...
by torzdf
Tue Jul 27, 2021 9:29 am
Forum: Convert Discussion
Topic: Converting A->A or B->B
Replies: 4
Views: 1075

Re: Converting A->A or B->B

Well.... It would only change if from B to A if you started sending it B's faces.

By swapping the model you our swapping the decoder, so you will get "A"s decoder rather than "B"'s

by torzdf
Mon Jul 26, 2021 8:54 am
Forum: Installation Support
Topic: "Failed to extract font properties" when start Faceswap.
Replies: 1
Views: 1108

Re: "Failed to extract font properties" when start Faceswap.

This looks like a corrupt font file to me.

This isn't specific to faceswap, so google might give you the best idea for a solution:
https://stackoverflow.com/questions/486 ... -load-face

by torzdf
Mon Jul 26, 2021 8:51 am
Forum: Convert Discussion
Topic: Converting A->A or B->B
Replies: 4
Views: 1075

Re: Converting A->A or B->B

Sure. Select the swap option in convert settings to swap which decoder is used.

by torzdf
Sun Jul 25, 2021 10:15 pm
Forum: Extract Discussion
Topic: Feature Request: Make Use of NVIDIA Hardware Video Decoding/Encoding with FFmpeg
Replies: 8
Views: 2088

Re: Feature Request: Make Use of NVIDIA Hardware Video Decoding/Encoding with FFmpeg

Python itself is single threaded, but it can (and we do) use multiprocessing libs.

As to FFMPEG, as we have to read the frames linearly, it may just not be possible to run it more optimally. To be honest, I have not dug into it in that much detail

by torzdf
Sun Jul 25, 2021 2:00 pm
Forum: Training Support
Topic: crash report while training: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize
Replies: 9
Views: 1957

Re: crash report while training: Failed to get convolution algorithm. This is probably because cuDNN failed to initializ

Glad to hear it.

You shouldn't have any global Cuda installed though. Whilst it may work now, it will probably break again in future if/when we upgrade.

We install Cuda locally in the Faceswap environment. Any global install may conflict.

by torzdf
Sun Jul 25, 2021 11:55 am
Forum: Training Support
Topic: crash report while training: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize
Replies: 9
Views: 1957

Re: crash report while training: Failed to get convolution algorithm. This is probably because cuDNN failed to initializ

You still have Cuda installed: gpu_cuda: 9.1 The version listed by nvidia-smi is the maximum version supported by your driver. The version that should be being used is the conda package cudatoolkit 10.1.243 h6bb024c_0 Having a system install + a conda install can conflict. Work on getting 9.1 fully ...
by torzdf
Sun Jul 25, 2021 11:25 am
Forum: Training Support
Topic: crash report while training: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize
Replies: 9
Views: 1957

Re: crash report while training: Failed to get convolution algorithm. This is probably because cuDNN failed to initializ

The next thing to do is to uninstall the global Cuda 9.1 you have installed. It is incompatible.

Reboot and try again.

by torzdf
Sun Jul 25, 2021 10:39 am
Forum: Swap Showcase
Topic: Phaze-A - 256px Demo
Replies: 10
Views: 10165

Re: Phaze-A - 256px Demo

I'll add to the above, it's not just legacy faces. The input resolution to the model is separate from the size of the extracted faces Try not to think of the extracted faces as the training images, rather, they contain the training images. Whether you use Face or legacy centering, the actual images ...
by torzdf
Fri Jul 23, 2021 10:14 am
Forum: Extract Discussion
Topic: Feature Request: Make Use of NVIDIA Hardware Video Decoding/Encoding with FFmpeg
Replies: 8
Views: 2088

Re: Feature Request: Make Use of NVIDIA Hardware Video Decoding/Encoding with FFmpeg

There is, but it means using the cli. One day I would like to add the possibility of batch processing to Faceswap, but see my earlier explanation of the massive to do list ;) I believe you are using Windows, so this wouldn't work for you (I use Linux), however a quick google around for Windows scrip...
by torzdf
Thu Jul 22, 2021 5:14 pm
Forum: Training Support
Topic: Crash while trying to train - OSError: Unable to open file (truncated file)
Replies: 3
Views: 3427

Re: Crash while trying to train - OSError: Unable to open file (truncated file)

I was going to say "please search prior to posting support requests". But.... This questions was already asked... by you... just a month ago.

by torzdf
Thu Jul 22, 2021 10:24 am
Forum: Convert Support
Topic: CPU temperature problem
Replies: 2
Views: 1741

Re: CPU temperature problem

Converting is CPU intensive. That's just the way it is.

You can try limiting them number of jobs, or run in "single-process" mode within the settings section