Search found 614 matches

by bryanlyon
Mon Jun 21, 2021 4:21 am
Forum: Training Discussion
Topic: Putting single photo B face on model?
Replies: 2
Views: 1041

Re: Putting single photo B face on model?

One image just isn't how FS works. It will never get unblurry with a single image. I'd suggest if you want to do that go check out First Order Model or "one-shot" solutions.

by bryanlyon
Mon Jun 21, 2021 4:19 am
Forum: Training Discussion
Topic: What is most important in lighting data? Shadows? Resolution?
Replies: 2
Views: 24

Re: What is most important in lighting data? Shadows? Resolution?

Loss is a poor measure, especially if you control one side of the data. I'd say that the most important thing is Variety. Variety is key because the model can learn all the different types of lighting itself. I'd suggest trying to move a light across the face to get different angles. Getting some fi...
by bryanlyon
Mon Jun 21, 2021 4:01 am
Forum: Training Support
Topic: How much memory for 256 resolution Dfaker?
Replies: 1
Views: 2219

Re: How much memory for 256 resolution Dfaker?

Unfortunately it's not an easy question to answer. It depends on FAR too many variables. You can try it (at a low batch size) and see if it'll work for you. But everything from your OS, to your driver version, to your web browser can effect the amount of vram it takes to train.

by bryanlyon
Mon Jun 21, 2021 3:12 am
Forum: Installation Support
Topic: Problem with new FS version, downgrade
Replies: 3
Views: 43

Re: Problem with new FS version, downgrade

Model collapses can happen anytime and are COMPLETLEY unrelated to the alignments. In fact, alignments are not ever fed into the model itself, and are only used to store masks and the like. Downgrade is possible, but your data will almost definitely need to be re-extracted and created. To do it you'...
by bryanlyon
Mon Jun 21, 2021 3:07 am
Forum: Extract Discussion
Topic: Masking hats and hair
Replies: 1
Views: 33

Re: Masking hats and hair

Mask out anything that you don't want to swap in. You might want to check out the new Bisenet masker. It gives you more options and accuracy.

by bryanlyon
Mon Jun 21, 2021 3:05 am
Forum: Training Discussion
Topic: Model collapse while Training Phaze-A
Replies: 1
Views: 8

Re: Difficulty Training Phaze-A

Unfortunately a model can collapse at any time. I'd suggest trying again, and if you still have problems, try reducing your Learning Rate.

by bryanlyon
Fri Jun 18, 2021 7:42 pm
Forum: Installation Support
Topic: Totally lost on how to install on newest MacBook Air, macOS Big Sur
Replies: 3
Views: 1443

Re: Totally lost on how to install on newest MacBook Air, macOS Big Sur

Unfortunately, we're still at the point where none of the developers have an M1 mac and so cannot develop for it. If anyone who does have an M1 would like to give it a try, you can install https://developer.apple.com/metal/tensorflow-plugin/ the Plugin for tensorflow metal and see if you can get it ...
by bryanlyon
Fri Jun 04, 2021 5:55 pm
Forum: Hardware
Topic: Hardware best practices
Replies: 58
Views: 34328

Re: Hardware best practices

Thank you sir, you are a gentleman and a scholar. Is there a better value card than the 3060 ti? Right now desktop GPUs are all but impossible to get ahold of. Honestly, whichever one you can get is probably going to be the one you want ;). I'd suggest checkout out Cloud options or if those aren't ...
by bryanlyon
Fri Jun 04, 2021 5:35 pm
Forum: Hardware
Topic: Hardware best practices
Replies: 58
Views: 34328

Re: Best CPU, Ram And GPU?

Are more than 4 CPU Cores used effectively? Is an 8 core utilized enough to justify it? What about a 16 core? How much Ram is optimal, 16GB, 32GB, more? Is the amount of VRAM on a GPU the most important aspect? I was thinking about getting a NVIDIA 3060 12GB version. Are there better options for th...
by bryanlyon
Mon May 31, 2021 5:26 pm
Forum: Training Support
Topic: Failed to start training
Replies: 4
Views: 1681

Re: Failed to start training

You can copy/paste the error messages when they show. That said I think your problem is a corrupt model file. Try the restore tool.

by bryanlyon
Wed May 26, 2021 9:59 pm
Forum: Artificial Intelligence
Topic: Creating virtual face
Replies: 1
Views: 3389

Re: Creating virtual face

That exact website you linked, on the bottom right, actually includes links to the software they're using (StyleGAN 2).

by bryanlyon
Wed May 26, 2021 9:57 pm
Forum: Cloud Discussion
Topic: Doubts about the use of google colab
Replies: 1
Views: 1482

Re: Doubts about the use of google colab

We have no official notebook for Colab and cannot provide assurances that it isn't doing anything malicious (same as Google themselves, hence that warning).

If you're worried you can audit the notebook code yourself or follow a guide for the official version on a bare server.

by bryanlyon
Wed May 19, 2021 3:27 pm
Forum: Training Discussion
Topic: "High quality sources" vs. "training only uses 64x64 image"
Replies: 1
Views: 3125

Re: "High quality sources" vs. "training only uses 64x64 image"

Quality means noise/variety more than high resolution. You don't want a whole bunch of low bitrate youtube videos since the compression artifacts lead to visible face distortion. You don't have to get everything from 4k Blu-rays but you want as good of quality as possible in order to minimize the is...
by bryanlyon
Wed May 19, 2021 3:22 pm
Forum: Extract Discussion
Topic: perfect source material? (posing and perspectives)
Replies: 2
Views: 2536

Re: perfect source material? (posing and perspectives)

VARIETY. Get a lot of different poses, expressions, and lighting situations. Film inside in full light, film with a single front light, film with a backlight, film outdoors, all while making various expressions and looking in different directions. Poke Deep Homage on the Discord as he has more speci...
by bryanlyon
Tue May 11, 2021 3:37 pm
Forum: General Discussion
Topic: Challenges faceswapping VR videos
Replies: 12
Views: 5531

Re: Challenges faceswapping VR videos

Here is a video on dewarping that may answer your questions.

I'm unaware of any simple tool that will automatically dewarp on command.

by bryanlyon
Tue May 11, 2021 3:20 am
Forum: Extract Discussion
Topic: Video Source Consolidation Workflow
Replies: 10
Views: 3041

Re: Video Source Consolidation Workflow

gravitation wrote: Tue May 11, 2021 1:30 am

You can save the encoder for reuse, but the decoders work best from scratch.

How would I go about doing that? Is it as simple as providing a h5 in the Load Weights under the Train > Model section?

Yup, exactly ;)

by bryanlyon
Tue May 11, 2021 12:44 am
Forum: Extract Discussion
Topic: Video Source Consolidation Workflow
Replies: 10
Views: 3041

Re: Video Source Consolidation Workflow

What I'd suggest is to learn batch scripting (or bash scripting in Linux) which can easily be used to extract multiple files at once.

On reusing part of the model: You can save the encoder for reuse, but the decoders work best from scratch.

by bryanlyon
Mon May 10, 2021 6:25 pm
Forum: Extract Discussion
Topic: Video Source Consolidation Workflow
Replies: 10
Views: 3041

Re: Video Source Consolidation Workflow

I think the big question is WHY are you trying to do it in this way? Are you trying to convert it all at once? Or are you using this collection for training? If the training, you don't need to merge the .fsa files, you just put the files you want to train with in a single directory. If it's for conv...
by bryanlyon
Mon Apr 26, 2021 8:01 pm
Forum: Training Support
Topic: Cant use images smaller than 256x256, just stops with error 3221225620
Replies: 3
Views: 1834

Re: Cant use images smaller than 256x256, just stops with error 3221225620

Errors with codes like that are all coming from upstream code, not FS itself (though may be caused by FaceSwap). In this case, the error is a divide by zero error. However, I think you may be looking at the resolution incorrectly. Why are you giving it small images? If it's extracted, I HIGHLY recom...
by bryanlyon
Fri Apr 02, 2021 5:23 pm
Forum: Training Support
Topic: No data to graph for selected session after an electricity blackout
Replies: 1
Views: 1969

Re: No data to graph for selected session after an electricity blackout

Looks like the power outage happened while it was saving. Luckily we create backups and you can restore it simply using the restore tool (Tools > Restore in the GUI, or python tools.py restore -h from the cli).