Thank you very much for the response.
Also I want to ask is it necessary to train a new model everytime I change the destination video? I want the same person(from src) in different videos. If I retrain the src with new dst video ,it shows lot of loss. So i wanna what you recommend.
Search found 4 matches
- Sat Sep 12, 2020 3:54 pm
- Forum: Training Discussion
- Topic: What things contribute to the best result?
- Replies: 6
- Views: 8221
Re: What things contribute to the best result?
- Fri Sep 04, 2020 6:26 pm
- Forum: Installation Support
- Topic: Error deleting Conda Virtual Environment
- Replies: 1
- Views: 4171
Error deleting Conda Virtual Environment
Im getting this error while installation Im running WIndows 10 (check) CPU Supports AVX Instructions (check) CPU Supports SSE4 Instructions (check) Completed check for installed applications (check) Setting up for: nvidia Downloading Miniconda3... Installing Miniconda3. This will take a few minutes....
- Fri Sep 04, 2020 5:55 pm
- Forum: Training Discussion
- Topic: What things contribute to the best result?
- Replies: 6
- Views: 8221
Re: What things contribute to the best result?
İ actually tried doing 250k iterations on a 12 min video (On DeepFaceLab), everything looked ok except the mouth wasn't moving how it was supposed to.
The mouth was just shut
Any idea why's this happening? Does the same happen on faceswap? Can İ create deepfake using only few different images?
- Fri Sep 04, 2020 5:28 am
- Forum: Training Discussion
- Topic: What things contribute to the best result?
- Replies: 6
- Views: 8221
What things contribute to the best result?
Suppose I want to create a star wars deepfake ,will lower resolution of video work better or it doesnt matter? how does it affect performance? Do lower resolution videos require more iterations to get satisfactory result? or again it doesnt matter. I have a 1050ti so Trial and Error is gonna take a ...