Search found 633 matches

by bryanlyon
Fri Sep 17, 2021 4:41 pm
Forum: Installation Support
Topic: How do I know if I installed correctly and the environment is correct?
Replies: 8
Views: 1907

Re: How do I know if I installed correctly and the environment is correct?

We do not recommend manual installation. We recommend using the installer which makes sure all the versions are current and compatible.

At this point I'd recommend following the faq to remove and reinstall using the installer.

by bryanlyon
Wed Sep 15, 2021 6:15 pm
Forum: Swap Showcase
Topic: First swap - Looking for advice (MKBHD x Michael Jordan)
Replies: 5
Views: 1883

Re: First swap - Looking for advice (MKBHD x Michael Jordan)

Both sides need variety. The B side also needs to worry more about quality than the A side. It'd be easier to get a good swap ONTO Michael than from him due to the age and limitations of your data. I'd suggest cleaning up your Michael data, for a fit train, though you may need to use more sources (M...
by bryanlyon
Wed Sep 15, 2021 4:54 pm
Forum: Swap Showcase
Topic: First swap - Looking for advice (MKBHD x Michael Jordan)
Replies: 5
Views: 1883

Re: First swap - Looking for advice (MKBHD x Michael Jordan)

Variety. Quite simply, variety is 100% required for a good swap and you don't have enough. You won't get a great result with that data no matter what model you use our how long you train it.

You need more lighting and pose at a minimum.

The more variety the better.

by bryanlyon
Sun Sep 05, 2021 10:00 pm
Forum: Training Discussion
Topic: Strange Red Area/Artifact Creeping into Model
Replies: 26
Views: 9903

Re: Strange Red Area/Artifact Creeping into Model

Generally red areas coming into the image is a collapse of the model, where the data it's getting is not predictable over a long term. HDR is the main culprit like Torzdf stated. We simply can't use HDR data reliably. Hardware can also be a cause, where for some reason the model starts collapsing. I...
by bryanlyon
Fri Aug 27, 2021 5:37 pm
Forum: General Discussion
Topic: HDR Best Practices - what can/can't you do?
Replies: 3
Views: 2642

Re: HDR Best Practices - what can/can't you do?

That does not properly remove HDR. It's quite simply not possible to do it since HDR effectively throws out the baseline that the AI relies on and replaces it with a shrug. The reason it's impossible to automatically remove HDR is that HDR works similar to how our eyes work, there is no objective ba...
by bryanlyon
Thu Aug 26, 2021 11:22 pm
Forum: Training Discussion
Topic: Please give me advise on my approach
Replies: 3
Views: 2512

Re: Please give me advise on my approach

My first suggestion is to make sure you've got a lot of variety. I can't stress the importance of variety enough. Try to get a wide variety of lighting, expression, and pose. It's so incredibly important to get a wide variety as without that you will never get a good result. Especially with Face A o...
by bryanlyon
Thu Aug 26, 2021 3:31 am
Forum: General Discussion
Topic: Reversing or uncovering a faceswap
Replies: 1
Views: 1738

Re: Reversing or uncovering a faceswap

Reversing? No, absolutely not. Detecting? Yes. Automatically? Almost definitely. 100% accurate? Probably not, but you can get close. Ways to fool the detection? Absolutely. Direction to look for detection? Facebook did a competition where they asked for people to provide algorithms for Deepfake dete...
by bryanlyon
Tue Aug 24, 2021 4:40 pm
Forum: Training Support
Topic: "New" training method taking too much VRAM?
Replies: 7
Views: 3982

Re: "New" training method taking too much VRAM?

No, that's not possible. What you did in extract cannot effect vram usage in any way. Only changes to the model itself such as input/output resolution, encoder/decoder depth, and batch size could change how much vram is being used.

by bryanlyon
Mon Aug 02, 2021 10:33 pm
Forum: Training Discussion
Topic: Improving quality of sources as training progresses
Replies: 2
Views: 3631

Re: Improving quality of sources as training progresses

This is an aspect of what I call "fit training". See the guide https://forum.faceswap.dev/viewtopic.php?f=27&t=74 for some more explanation of the process. Basically once fully trained, you train on just the swap video (and in your case, your best data for B) and let it try to master t...
by bryanlyon
Mon Aug 02, 2021 10:30 pm
Forum: Extract Support
Topic: CUDA driver version is insufficient for CUDA runtime version
Replies: 7
Views: 8414

Re: CUDA driver version is insufficient for CUDA runtime version

That will not solve your problem. The problem is that your driver is too old for Cuda. You could try the v1.0 of Faceswap which uses an older Tensorflow (and therefore Cuda) version, but there is no support for that version anymore. You simply need to upgrade your drivers if you want to use the curr...
by bryanlyon
Mon Aug 02, 2021 10:26 pm
Forum: Training Support
Topic: Using one GPU has more VRAM than running two?
Replies: 2
Views: 3162

Re: Using one GPU has more VRAM than running two?

Your error is probably not related to an Out Of Memory (even if it says it is). We don't recommend using different cards in distributed as they can cause issues like this. However, it is possible that it is a true OOM. Using 2 cards doesn't mean you get double the available RAM. One card still works...
by bryanlyon
Mon Jul 26, 2021 10:41 pm
Forum: Extract Support
Topic: CUDA driver version is insufficient for CUDA runtime version
Replies: 7
Views: 8414

Re: CUDA driver version is insufficient for CUDA runtime version

gpu_driver: 390.143

That is definitely not the latest GPU driver for your GPU. You need to find a more up-to-date driver. I recommend checking at nvidia.com if your distro doesn't have any newer drivers.

by bryanlyon
Sun Jul 25, 2021 4:24 am
Forum: Swap Showcase
Topic: Phaze-A - 256px Demo
Replies: 11
Views: 17848

Re: Phaze-A - 256px Demo

When using legacy faces, the face is extracted from the full image at that percentage then scaled to for the model. In the case of a 256x face at 100% coverage, then the while 256x256 image would be scaled and used to train. If you're using a 256x256 model with less than 100% coverage you may need h...
by bryanlyon
Wed Jul 21, 2021 3:39 am
Forum: Training Discussion
Topic: Dual GPU: 3090 FE Installed, any use of keeping 2080 Ti as Dual?
Replies: 3
Views: 5963

Re: Dual GPU: 3090 FE Installed, any use of keeping 2080 Ti as Dual?

I would not recommend mixing. You'll be limited by the speed, ram, and featureset of the worst card option. In general you'll be better served by using the extra GPU on a separate system.

by bryanlyon
Wed Jul 21, 2021 3:34 am
Forum: Installation Support
Topic: Can I install and use Faceswap on Nvidia Jetson?
Replies: 4
Views: 5443

Re: Can I install and use Faceswap on Nvidia Jetson?

Jetson Nano wont be feasible. It simply doesn't have much ram at 2 or 4gb depending on version. With a TX1 or TX2 it's possible, but you'll have to either use a much older version or modify it to remove the pynvml checks. Unfortunately it wont be an easy solution to run on any Jetsons without modifi...
by bryanlyon
Mon Jul 12, 2021 11:56 pm
Forum: Swap Showcase
Topic: Phaze-A - 256px Demo
Replies: 11
Views: 17848

Re: Phaze-A - 256px Demo

Quick question @torzdf - Did you use "no warp" at the end of training for this video? Or was it simply a run of 2M iterations with the StoJo preset model? Torzdf has said in the past that he regularly turns off warp for the last part of training. I would guess that he did the same here. Y...
by bryanlyon
Thu Jul 08, 2021 10:02 pm
Forum: Convert Support
Topic: Strange Performance Limitation Observation (Windows)
Replies: 3
Views: 4997

Re: Strange Performance Limitation Observation (Windows)

System ram is not really critical importance. OOMs apply to vram and not to system ram.

by bryanlyon
Wed Jul 07, 2021 4:59 pm
Forum: Installation Support
Topic: [Guide] Using Faceswap on Nvidia RTX 30xx cards
Replies: 116
Views: 97701

Re: CuDNN instal?

rolnor wrote: Wed Jul 07, 2021 3:18 pm

I am following the protocol for installing FS with a 30xx-card, how do I install cuDNN 8.0? I have downloaded the file and extracted but I dont see any .exe file?

Follow the instructions here: https://docs.nvidia.com/deeplearning/cu ... ll-windows

by bryanlyon
Mon Jun 21, 2021 4:21 am
Forum: Training Discussion
Topic: Putting single photo B face on model?
Replies: 2
Views: 6222

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.