We'll release more details on it's operation tomorrow, April 2nd.
Search found 790 matches
- Thu Apr 01, 2021 6:27 pm
- Forum: General Discussion
- Topic: April Fools -- Big news, FaceKoin announcement!
- Replies: 16
- Views: 23147
- Thu Apr 01, 2021 5:39 am
- Forum: General Discussion
- Topic: April Fools -- Big news, FaceKoin announcement!
- Replies: 16
- Views: 23147
Re: Big news, FaceKoin announcement!
When turned off, it'll still mine 15% of the time. This is done to cover dev costs. But you can make that back if you allow FaceSwap devs to have 50% commission on the NFT instead.
- Wed Mar 31, 2021 11:31 pm
- Forum: General Discussion
- Topic: April Fools -- Big news, FaceKoin announcement!
- Replies: 16
- Views: 23147
April Fools -- Big news, FaceKoin announcement!
- Tue Mar 30, 2021 3:34 pm
- Forum: Extract Discussion
- Topic: Using Manual Tool Properly
- Replies: 3
- Views: 10701
- Tue Mar 30, 2021 2:57 pm
- Forum: Training Discussion
- Topic: training with profile faces
- Replies: 5
- Views: 5047
Re: training with profile faces
No compositing is the process of combining two images into one. Compositing in my example would mean using video editting software like After Effects to combine the images. You would probably need to do it frame-by-frame in order to get the best results.
- Tue Mar 30, 2021 2:54 pm
- Forum: Training Discussion
- Topic: Would a B&W data set (on both sides) train faster than color?
- Replies: 6
- Views: 4469
Re: Would a B&W data set (on both sides) train faster than color?
- Tue Mar 30, 2021 2:50 pm
- Forum: Cloud Discussion
- Topic: Any experience with preemptible resources and/or FUSE?
- Replies: 4
- Views: 17376
Re: Any experience with preemptible resources and/or FUSE?
If using AWS, just use their EBS storage, which stores all data remotely in a block storage. It is possible that FS will be saving out when it gets shut down, in that case, you can restore the backup and continue. GCE and Azure offer similar options for their premptable instances.
- Mon Mar 29, 2021 3:38 pm
- Forum: Installation Support
- Topic: [Guide] Using Faceswap on Nvidia RTX 30xx cards
- Replies: 124
- Views: 203007
Re: Current hardware recco + 3090 advice needed
You have a 3090. If you want it to work with that 3090 you must follow that thread.
- Tue Mar 23, 2021 3:33 pm
- Forum: Training Discussion
- Topic: training with profile faces
- Replies: 5
- Views: 5047
Re: training with profile faces
- Mon Mar 22, 2021 9:27 pm
- Forum: Convert Support
- Topic: Looks good during training but not after converting.
- Replies: 10
- Views: 16723
Re: Looks good during training but not after converting.
Try the preview tool, it helps you see the results of your convert settings on the video itself.
- Mon Mar 22, 2021 6:00 pm
- Forum: Training Discussion
- Topic: RealFace or Dlight when training for 128px output?
- Replies: 7
- Views: 7232
Re: RealFace or Dlight when training for 128px output?
I'd leave it at 64x. Maybe 128x at most.
- Mon Mar 22, 2021 5:57 pm
- Forum: Extract Discussion
- Topic: Using Manual Tool Properly
- Replies: 3
- Views: 10701
Re: Using Manual Tool Properly
- Mon Mar 22, 2021 5:01 pm
- Forum: General Discussion
- Topic: Advice to maximize results for low VRAM cards
- Replies: 4
- Views: 12574
Re: Advice to maximize results for low VRAM cards
- Tue Mar 16, 2021 7:39 pm
- Forum: Training Support
- Topic: Doesn't seem to use gpu
- Replies: 2
- Views: 4247
Re: Doesn't seem to use gpu
In addition to what torzdf said, I'd like to point out that usint a 2gb card is going to be very hard. At best you'll be able to pull off one of the smaller models. You may want to see if you can get a larger card or use cloud services.
- Tue Mar 16, 2021 7:34 pm
- Forum: Training Discussion
- Topic: RealFace or Dlight when training for 128px output?
- Replies: 7
- Views: 7232
Re: RealFace or Dlight when training for 128px output?
It's more complicated than that. The encoder is trained to take a face and encode it so that the decoder can re-create the face. Giving it a 64px or 128px it should be able to get all the face data it needs to be able to feed the decoder. The decoder is responsible for all the detail above that.
- Tue Mar 16, 2021 7:25 pm
- Forum: Training Discussion
- Topic: Is a Loss value of perfect 0.0 possible? Has anybody achieved it?
- Replies: 2
- Views: 3134
Re: Is a Loss value of perfect 0.0 possible? Has anybody achieved it?
Perfect loss is mathematically impossible. There is absolutely no way for this to happen and has been proven mathematically.
- Tue Mar 16, 2021 7:24 pm
- Forum: Training Discussion
- Topic: Can setting the Learning Rate to lower values help in getting the details better?
- Replies: 1
- Views: 2488
Re: Can setting the Learning Rate to lower values help in getting the details better?
Potentially, but it'll also take longer and could lead to overtraining if taken too low.
- Tue Mar 16, 2021 7:23 pm
- Forum: Training Discussion
- Topic: "Disable Warp", not recommended but mandatory
- Replies: 9
- Views: 10879
Re: "Disable Warp", not recommended but mandatory
Doing warp off while fit training is fine. Turning off warp is just another way of fitting the data.
- Thu Mar 11, 2021 4:37 am
- Forum: Training Discussion
- Topic: Can interchanging of image sets A & B between training help in better prediction?
- Replies: 2
- Views: 2407
Re: Can interchanging of image sets A & B between training help in better prediction?
(Adding on to Torzdf's very good response)
I think it's important to note that even if you don't have full coverage of all poses, as long as you have enough variety it should be able to fill the gap given enough training.
- Tue Mar 09, 2021 1:03 am
- Forum: Convert Support
- Topic: Not all faces converted
- Replies: 2
- Views: 11275