Even though semiconductor devices are fine, substrates will be cured by constant heat and will affect GPU life.
Search found 6 matches
- Thu Aug 13, 2020 8:36 am
- Forum: Hardware
- Topic: Has deepfaking for long periods caused anyone long-term hardware issues?
- Replies: 9
- Views: 7861
- Thu Aug 06, 2020 5:16 pm
- Forum: Training Discussion
- Topic: Comparing model types with examples
- Replies: 23
- Views: 70716
Re: Comparing models with examples
On average, DFL-SAE seems to be able to achieve fast and reasonable results.
- Tue Aug 04, 2020 12:25 pm
- Forum: Training Discussion
- Topic: Can't I continue to use one Model Dir?
- Replies: 7
- Views: 3246
- Tue Aug 04, 2020 12:12 pm
- Forum: Training Discussion
- Topic: Can't I continue to use one Model Dir?
- Replies: 7
- Views: 3246
Re: Can't I continue to use one Model Dir?
Are you asking about resuming a new model? Or starting a new one like Dfaker , Lightweight, ect, in the same model folder? Same model / based on original train options. Leave A(base) alone and change B image only. From what I feel, this method is faster than training from the beginning. Then can I ...
- Tue Aug 04, 2020 10:06 am
- Forum: Training Discussion
- Topic: Can't I continue to use one Model Dir?
- Replies: 7
- Views: 3246
Re: Can't I continue to use one Model Dir?
If you use a model trained on a different set of faces It wont work well. The model learns Original(A) to Target (B) . If you change the A face, the trained model will not exactly understand. The resulting face will look not great, really blurry, and sometimes monstrous. If keep using one Model dir...
- Tue Aug 04, 2020 9:08 am
- Forum: Training Discussion
- Topic: Can't I continue to use one Model Dir?
- Replies: 7
- Views: 3246
Can't I continue to use one Model Dir?
Why do we need to add a new model whenever the target changes? 