Search found 218 matches

by bryanlyon
Mon Apr 06, 2020 6:17 pm
Forum: Artificial Intelligence
Topic: Voice swap ?
Replies: 7
Views: 1311

Re: Voice swap ?

Oh god, that site sounds HORRIBLE.
by bryanlyon
Wed Apr 01, 2020 8:54 pm
Forum: Convert
Topic: ERROR Failed to convert image: Unable to allocate array with shape...
Replies: 1
Views: 38

Re: ERROR Failed to convert image: Unable to allocate array with shape...

This is a memory related error, yes. 4GB of system RAM is really just not enough and is causing problems in this case. You can try switching to a SIngle job (set jobs to 1) and see if that helps, but I think you're likely to need an upgrade to your system RAM before you'll be able to do much with Fa...
by bryanlyon
Tue Mar 31, 2020 10:47 pm
Forum: Convert
Topic: Alignment Files
Replies: 4
Views: 124

Re: Alignment Files

It's there, try reading from the start.
by bryanlyon
Tue Mar 31, 2020 10:46 pm
Forum: General Chat
Topic: Thinking about writing a newbie guide
Replies: 3
Views: 48

Re: Thinking about writing a newbie guide

Yes, we welcome any guides you want to make. People keep asking for a video guide if that sounds doable, we'd appreciate it. Even if it's text, it may be helpful.
by bryanlyon
Mon Mar 30, 2020 5:55 pm
Forum: Hardware
Topic: i5-9400 vs. i7-9700 Processor ?
Replies: 2
Views: 35

Re: i5-9400 vs. i7-9700 Processor ?

See the hardware guide at viewtopic.php?f=16&t=10 .
by bryanlyon
Tue Mar 24, 2020 4:08 am
Forum: Hardware
Topic: Dual p106-6gb
Replies: 11
Views: 151

Re: Dual p90-6gb

When I say use the benchmark, I just mean use it for a short time while you start the training process, but you should still use both for Faceswap. It's just there to "clear the hurdle" of the demand spike. You'll probably have an easier time of lowering the power needs.
by bryanlyon
Mon Mar 23, 2020 9:59 pm
Forum: Hardware
Topic: GTX 1650 Super 4Gb - Optimizer savings enabled - train
Replies: 2
Views: 56

Re: GTX 1650 Super 4Gb - Optimizer savings enabled - train

This is probably due to drivers/Windows more than the card. Quadro cards use different drivers and probably reserved less memory for OS use, leaving more memory for Faceswap. Windows will often reserve 1/4-1/2 your total vram. 4gb is really close to the minimum we support, and it's likely that you'r...
by bryanlyon
Mon Mar 23, 2020 9:30 pm
Forum: Hardware
Topic: Dual p106-6gb
Replies: 11
Views: 151

Re: Dual p90-6gb

Chances are this is due to a slow response by your PSU to the sudden demand of 2 GPUs. This is probably creating a "brown out" type situation where due to a temporary voltage drop your system hangs. Faceswap (like most GPU compute tasks) can cause a sudden spike in voltage draw when first starting. ...
by bryanlyon
Mon Mar 23, 2020 5:12 pm
Forum: General Chat
Topic: Step to create DeppFake with Faceswap
Replies: 2
Views: 90

Re: Step to create DeppFake with Faceswap

Yes, you need to extract any videos you want to train with. It's highly recommended you use more than 2 videos. See viewtopic.php?f=5&t=27
by bryanlyon
Wed Mar 18, 2020 7:57 pm
Forum: Extract
Topic: alignment tool extract doesnt match alignment
Replies: 11
Views: 210

Re: alignment tool extract doesnt match alignment

Best way to avoid this may be to extract the video into the frames and go from there. Sadly there are all sorts of frame issues in videos which show up in different contexts. Extracting to PNGs is sometimes the only guarantee, but it's not perfect since recreating that video can be a pain.
by bryanlyon
Thu Mar 12, 2020 8:33 pm
Forum: General Chat
Topic: Way to notify training failure?
Replies: 5
Views: 323

Re: Way to notify training failure?

Maybe the devs can offer an option of adding IFTTT integration... Not really likely to happen. This would be extremely fiddly and cause issues for some workcases. You're going to do best finding a soltuion on your own. Something like keeping track of Python processes or using "generate" and adding ...
by bryanlyon
Thu Mar 12, 2020 6:25 pm
Forum: Extract
Topic: odd Training error
Replies: 13
Views: 331

Re: odd Training error

Glad you've got a work-around. This is unlikely to be directly fixed. The manual tool is currently under a complete rework so the current tool will not likely see any fixes or changes as the new one should be here soon and will fix issues like this.
by bryanlyon
Thu Mar 12, 2020 5:24 pm
Forum: Convert
Topic: Full Face not being replaced
Replies: 3
Views: 353

Re: Full Face not being replaced

Link was broken, I've fixed it, try again.
by bryanlyon
Thu Mar 12, 2020 3:36 pm
Forum: Convert
Topic: Full Face not being replaced
Replies: 3
Views: 353

Re: Full Face not being replaced

See viewtopic.php?f=6&t=74 especially the section titled "Avoid beards that go outside the face area".
by bryanlyon
Wed Mar 11, 2020 2:57 am
Forum: Extract
Topic: odd Training error
Replies: 13
Views: 331

Re: odd Training error

You can put it on Google Drive/Dropbox or similar. Feel free to PM a link if you don't want it public.
by bryanlyon
Wed Mar 11, 2020 2:42 am
Forum: Extract
Topic: odd Training error
Replies: 13
Views: 331

Re: odd Training error

Every time the mask tool runs, it creates a backup of the old alignments file. Make sure you're using the correct ones for all the tasks. Make sure that none of the processes fail or throw an error (make sure that the mask tool actually creates a new FSA and it should be larger than the previous one...
by bryanlyon
Wed Mar 11, 2020 2:31 am
Forum: Extract
Topic: odd Training error
Replies: 13
Views: 331

Re: odd Training error

Try again, chances are it errored out the first time and didn't actually generate the masks.
by bryanlyon
Tue Mar 10, 2020 4:33 pm
Forum: Training
Topic: Better A > B Swap than B > A on different trainer models (Newbie)
Replies: 2
Views: 274

Re: Better A > B Swap than B > A on different trainer models (Newbie)

For Dlight, this is an intended "feature" of the model. It saves memory on the A decoder in order to maximize the quality of the B side. This also applies to Realface and Unbalanced. All the other models you mentioned are symmetrical where the A and B sides are identical and you can swap both direct...
by bryanlyon
Fri Mar 06, 2020 5:23 pm
Forum: Training
Topic: Should I ever expect convergence? Couple of questions.
Replies: 2
Views: 337

Re: Should I ever expect convergence? Couple of questions.

On your questions: 1: Convergence isn't where the face is blurry, but where the model has learned all that it could. Either because you've hit the limit of your data, or the model. The face could still be blurry. 2: Original will probably converge in a couple days, and just not learn more. Villain c...