Faceswap Forum

I trained a model using villain using 85% coverage. After _250k iterations I did a test conversion and the results are reasonable, but there is a shadow on the temple/side of the forehead. I was thinking I was too aggressive with the coverage in the model, so is it possible to reduce coverage mid training, or is the coverage locked from the start and I need to train again from scratch?

Coverage is locked, as it basically dictates how much of the image is fed into the model. Changing coverage mid-train would basically destroy your model, so you will need to start again.

thanks for that final word.
back to scratch for the model.