The installer just downloads and installs from the github. If it's failing on conda then you might want to manually install miniconda and provide the path to the faceswap installer.
Search found 790 matches
- Mon Jan 03, 2022 10:41 pm
- Forum: Installation Support
- Topic: Strange Installing Errorcode during installation faceswap on Win 10?
- Replies: 10
- Views: 4669
- Mon Jan 03, 2022 4:31 pm
- Forum: Training Discussion
- Topic: Halo effect around face on side B causes side A to have halo effect and not cover full face.
- Replies: 3
- Views: 2003
Re: Halo effect around face on side B causes side A to have halo effect and not cover full face.
- Mon Jan 03, 2022 4:26 pm
- Forum: Training Discussion
- Topic: Training on rotated Images
- Replies: 3
- Views: 1715
Re: Training on rotated Images
Yeah, just use the augmentation setting. That's it's purpose. And while the slider only goes up to 25 degrees, it'll actually work with any number manually inserted.
- Mon Jan 03, 2022 4:25 pm
- Forum: Training Discussion
- Topic: Does adding Black and White footage to training data help or hinder?
- Replies: 3
- Views: 1438
Re: Does adding Black and White footage to training data help or hinder?
- Mon Jan 03, 2022 4:21 pm
- Forum: Installation Support
- Topic: Strange Installing Errorcode during installation faceswap on Win 10?
- Replies: 10
- Views: 4669
Re: Strange Installing Errorcode during installation faceswap on Win 10?
This is answered in our FAQ.
- Mon Jan 03, 2022 4:17 pm
- Forum: Extract Support
- Topic: The mask appears to be covered in two ways.
- Replies: 2
- Views: 1445
Re: The mask appears to be covered in two ways.
The zoomed in version is accurate.
- Mon Jan 03, 2022 4:12 pm
- Forum: Training Support
- Topic: How to improve training?
- Replies: 3
- Views: 5838
Re: How to improve training?
All required alignments for training are included in the training images. The .fsa is now used only for final conversion.
- Mon Jan 03, 2022 4:08 pm
- Forum: Convert Discussion
- Topic: Newbie question, artefacts on converting
- Replies: 1
- Views: 6588
Re: Newbie question, artefacts on converting
The mask you're using isn't removing the extra hair, I suggest using BiSeNet with the hair disabled to remove that.
- Tue Dec 28, 2021 9:16 pm
- Forum: Hardware
- Topic: question on the use of multiple gpus 8+
- Replies: 6
- Views: 2284
Re: question on the use of multiple gpus 8+
No. Latency is bad enough if the GPUs are all in one box. If you were to sync over a network you'd lose anything you could possibly gain from more GPUs.
- Tue Dec 28, 2021 8:48 pm
- Forum: Hardware
- Topic: question on the use of multiple gpus 8+
- Replies: 6
- Views: 2284
Re: question on the use of multiple gpus 8+
- Thu Dec 23, 2021 5:32 pm
- Forum: Artificial Intelligence
- Topic: Thesis: Facial scar faceswap
- Replies: 2
- Views: 7302
Re: Thesis: Facial scar faceswap
Should be feasible. Though you'll need to take resolution limits into account. Makeup has been done in the past successfully.
- Sun Dec 19, 2021 7:20 pm
- Forum: Training Support
- Topic: Possibility of Turning Off "Learn Mask" on an Active Training Model
- Replies: 3
- Views: 1329
Re: Possibility of Turning Off "Learn Mask" on an Active Training Model
Learn Mask changes the model itself in order to let it learn the mask. Unfortunately once a model is started, it can't be changed. You're going to be stuck with the mask being learned, that said, once convert comes up, you can just not use the predicted mask.
- Sat Dec 18, 2021 7:25 pm
- Forum: Extract Support
- Topic: How to remove the padding from the extracted faces
- Replies: 4
- Views: 4071
Re: How to remove the padding from the extracted faces
- Thu Dec 16, 2021 3:23 pm
- Forum: Hardware
- Topic: GPU RAM Size vs. TFLOPS: which matters more?
- Replies: 5
- Views: 6227
Re: GPU RAM Size vs. TFLOPS: which matters more?
- Thu Dec 16, 2021 3:15 pm
- Forum: Training Discussion
- Topic: Training on rotated Images
- Replies: 3
- Views: 1715
Re: Training on rotated Images
- Thu Dec 09, 2021 3:56 pm
- Forum: Training Support
- Topic: CRITICAL NaN Detected and cannot train
- Replies: 2
- Views: 1530
Re: CRITICAL NaN Detected and cannot train
- Tue Nov 30, 2021 3:51 pm
- Forum: Hardware
- Topic: GPU RAM Size vs. TFLOPS: which matters more?
- Replies: 5
- Views: 6227
Re: GPU RAM Size vs. TFLOPS: which matters more?
3060 is my recommended card. See viewtopic.php?f=16&t=10
That said, right now it's the card you can get more than the card you want.
- Thu Nov 25, 2021 12:30 am
- Forum: Training Support
- Topic: Manually adjusting thousands of frames individually?
- Replies: 3
- Views: 4169
Re: Manually adjusting thousands of frames individually?
Short scenes let you focus your efforts. Even if you're doing large amounts of scenes, I recommend converting one at a time. It lets you tweak settings and efforts to get the best results for each situation.
- Wed Nov 24, 2021 11:31 pm
- Forum: Training Support
- Topic: Manually adjusting thousands of frames individually?
- Replies: 3
- Views: 4169
Re: Manually adjusting thousands of frames individually?
Generally you'll only want to fine-tune data that you're using for actual conversion. It's not worth fine-tuning thousands of files for training. Better to just delete bad images rather than tuning them.
- Wed Nov 24, 2021 4:50 pm
- Forum: Extract Support
- Topic: Not enough RAM to perform linkage clustering. Using vector clustering. This will be significantly slower.
- Replies: 2
- Views: 4715
Re: Not enough RAM to perform linkage clustering. Using vector clustering. This will be significantly slower.
Like it says, to use the faster clustering with that many images you'd need more than 700gb of RAM. It uses exponential amounts of RAM to cluster based on how many images you have. You can split it to subses of 50k images to sort it in 4 packs if you want to use the faster method.