Faceswap Forum

Fit training is replace all your data for A with the set you're actually going to swap. Changing B is unecessary but can also help avoid overtraining problems.. When I was using the Dlight model, I found that B Face training seemed to be faster. But what I actually want is to replace A Face with B ...

Thank you very much. I am a C# software engineer and just started learning this project. Thank you very much for your answer. Convert Result: Video : 1920X1072 Do you think continued training can improve the face picture quality（output size 384px）? For example, facial details, skin texture? The sam...

Model：Dlight Batch Size：4 Iterations: 520728 Will it be clearer if i continue training? https://i.loli.net/2020/09/22/MIEGdgVRwA8ZPk9.png https://i.loli.net/2020/09/22/V45GMn1KfXUA6wC.png config": { "coverage": 80, "optimizer": "adam", "learning_rate": 5e...