Faceswap Forum

You should be able to train on that card (I have trained on an AMD R9 290). AMD will train slower, and you won't be able to run the larger models. Original/dfaker should be fine though.

Yes. So ultimately, you are running out of VRAM. Outside of the standard fixes, you can try reducing settings on that model's config.

Otherwise, I would highly recommend dual booting Linux (Xubuntu is a good choice) for Faceswap, as you will have access to approximately 20% more VRAM.

Your output in that command is pointing to an alignments file.

I'm not entirely clear on what you're trying to do.

Ultimately, to swap faces (be it a single image or a video) then you need a trained model.

To have a trained model you need many many faces for both A and B to train on... so yes, unfortunately, the process is still the same.

/ key cycles frame zooming

Please provide your system info.

GUI Users: Go to Help -> Output system information

CLI Users: From inside your virtual environment, inside your faceswap folder, run:
python -c "from lib.sysinfo import SysInfo ; print(SysInfo().full_info())"

That log is just the debug log... Is it getting stuck there?

Please hit the Generate button in the GUI and post the command you are attempting to run. Thanks

Yeah, multiple models in the same folder can be problematic. We will be disabling the ability to have multiple models in one folder at some point.

Ok. It seems there was a requirement update on PlaidML which broke our dependencies.

I've pushed a fix, so hopefully this will fix it for you. Please clean everything out and try installing again.

Ok. Basically PlaidML is failing to load an internal file....

The next thing I would try is the following....

Start > Anaconda Prompt Follow the prompts to select a GPU, then try Faceswap again.

The most likely cause is a conflict somewhere.

I'm hoping our AMD guy shows up soon with some troubleshooting, but could you try to follow these steps and see if it resolves the issue?

app.php/faqpage#f1r1

Ignore it. They are internal Keras warnings.

Whilst this isn't currently directly an option in Faceswap, you *can* do this by setting an environment variable.

See here:
https://stackoverflow.com/questions/497 ... indows-cmd

So to rough-cut your extraction - use command prompt in your extraction directory and use the "del *_1.jpg" - BUT DON'T FORGET to follow the guide for sorting when photos are deleted. Hope that helps you out a bit. I don't recommend this. The order that detectors find faces is entirely arbitrary. L...

You can use several masks for one faceset? Hm, have you noticed better results with that? And would you have to restart training? Also, if you find the time, could you write out a brief workflow on how to use several masks. Thanks! I mean you can "store" several masks per faceset, not that you can ...

Should be fine. You can also add additional masks with the mask tool

Can you post the raw output from this command:

Ahh, that may be reserved RAM, rather than explicitly in use. Are you looking at the free column or the available column?

The total ram less available will give you a better indication of the amount of RAM actually being used.

For a first fake, that's very good. My first was far worse! You made a decent choice for source video for a first swap (mostly facing forwards)