The data is viewable. You can use the manual tool to view the alignments. The only part of the alignments.fsa file that isn't yet in the manual tool is the mask, which will be added in the new version that is currently in the works.
Search found 790 matches
- Wed Jan 29, 2020 2:36 am
- Forum: Extract Discussion
- Topic: viewing/modifying alignments.fsa?
- Replies: 7
- Views: 11508
- Wed Jan 29, 2020 1:55 am
- Forum: Extract Discussion
- Topic: viewing/modifying alignments.fsa?
- Replies: 7
- Views: 11508
Re: viewing/modifying alignments.fsa?
- Sun Jan 26, 2020 8:00 pm
- Forum: Hardware
- Topic: RTX Tensor Cores in Faceswap
- Replies: 4
- Views: 14778
Re: RTX Tensor Cores in Faceswap
- Sat Jan 25, 2020 8:57 pm
- Forum: Hardware
- Topic: Has deepfaking for long periods caused anyone long-term hardware issues?
- Replies: 9
- Views: 7912
Re: Has deepfaking for long periods caused anyone long-term hardware issues?
- Sat Jan 25, 2020 3:26 am
- Forum: Training Discussion
- Topic: New computer build issues
- Replies: 6
- Views: 3457
Re: New computer build issues
Batch size is the first one to try. If that's not enough you can go in to the model settings to reduce quality or you can enable memory options while training.
Ultimately you have 6gb of vram so can use most lighter models without too much trouble but will struggle with the larger models.
- Sat Jan 25, 2020 2:02 am
- Forum: Extract Support
- Topic: Not seeing the images on my computer when I try to pick a image
- Replies: 1
- Views: 2056
Re: Not seeing the images on my computer when I try to pick a image
- Fri Jan 24, 2020 7:57 pm
- Forum: General Discussion
- Topic: Has anyone made a VR deepfake before? Is it easy?
- Replies: 3
- Views: 13485
Re: Has anyone made a VR deepfake before? Is it easy?
There are other ways to unwarp, that's just one tutorial. But you will have to unwarp it before you can convert.
- Fri Jan 24, 2020 7:48 pm
- Forum: General Discussion
- Topic: Has anyone made a VR deepfake before? Is it easy?
- Replies: 3
- Views: 13485
Re: Has anyone made a VR deepfake before? Is it easy?
You first need to unwarp the VR video. See for example then only after you unwarp it can you convert it. Then you'll want to rewarp it back so it looks correct in VR.
- Wed Jan 22, 2020 5:08 am
- Forum: Training Support
- Topic: After training for 24+ hours, mask turns solid black, and lost A and lost B is nan
- Replies: 2
- Views: 2375
Re: After training for 24+ hours, mask turns solid black, and lost A and lost B is nan
This is a relatively common problem. Use the restore tool to load the backup and continue from the last good result.
- Mon Jan 20, 2020 8:54 pm
- Forum: Extract Discussion
- Topic: Creating masks for heavily obstructed faces
- Replies: 2
- Views: 2778
Re: Creating masks for heavily obstructed faces
Right now, if no masks work for you there isn't much you can do about it. Torzdf does have an updated manual tool in the works that will allow you to manually mask the face, but right now it is not yet available.
- Mon Jan 20, 2020 4:28 am
- Forum: Extract Support
- Topic: cuDNN failed to initialize
- Replies: 29
- Views: 15886
Re: Error when masking with Unet post extraction
This is often masking a memory error. If you've already turned on Allow Growth in the Extract plugins, you may try turning down the BatchSize in the Settings/Extract Plugins/Mask/Unet DFL.
- Mon Jan 20, 2020 4:23 am
- Forum: Training Discussion
- Topic: Speed/Quality and Batch size
- Replies: 6
- Views: 14836
Re: Speed/Quality and Batch size
viewtopic.php?f=6&t=146
This is the best source of information on this. Honestly, much more than what this guide shows is overthinking things. Just go for the largest Batch Size you can without turning on any memory hacks (as those slow down training for Vram).
- Sat Jan 18, 2020 7:08 pm
- Forum: Training Discussion
- Topic: Speed/Quality and Batch size
- Replies: 6
- Views: 14836
Re: Speed/Quality and Batch size
- Sat Jan 18, 2020 5:27 pm
- Forum: General Discussion
- Topic: Nvidia recently posted information saying that NVME could be used as
- Replies: 1
- Views: 3009
Re: Nvidia recently posted information saying that NVME could be used as
- Sat Jan 18, 2020 6:10 am
- Forum: Training Support
- Topic: Failed and return code: 3221225477
- Replies: 3
- Views: 3660
Re: Failed and return code: 3221225477
- Fri Jan 17, 2020 5:44 pm
- Forum: Training Support
- Topic: Failed and return code: 3221225477
- Replies: 3
- Views: 3660
Re: Failed and return code: 3221225477
- Fri Jan 17, 2020 5:52 am
- Forum: Training Discussion
- Topic: No flip for specific faces
- Replies: 1
- Views: 1677
Re: No flip for specific faces
Any time there is a mark you want to preserve on one side of the face you should disable the flip option throughout the entire training process. If you do this please be aware that you'll want to include a significantly larger dataset to ensure the quality of the results.
- Thu Jan 16, 2020 4:00 pm
- Forum: Hardware
- Topic: Hardware best practices
- Replies: 83
- Views: 186657
Re: Hardware best practices
It's not critical. You could certainly get away without upgrading the CPU, but you WILL see better speeds if you upgrade it later. Might be worth scheduling it sometime down the line.
- Thu Jan 16, 2020 3:52 pm
- Forum: Hardware
- Topic: Hardware best practices
- Replies: 83
- Views: 186657
Re: Hardware best practices
- Wed Jan 15, 2020 1:33 am
- Forum: Cloud Discussion
- Topic: free genesiscloud gpus any good?
- Replies: 2
- Views: 6514
Re: free genesiscloud gpus any good?
I've never used it. They look fairly legit but you can never be sure. Maybe you'd rather try the free tier of Paperspace https://docs.paperspace.com/gradient/in ... -instances ?