Is it possible to change the zoom when re-extracting faces from an alignments file

[Dashon]

Hi

Just wondering if it's possible to change something in the settings to make re-extracting from alignments file produce face files that are less zoomed in.

I've been using dfl to detect and generate faces and clean up alignments from videos, but after I generate an alignments file using faceswap and re-extract the faces, I noticed that the resulting faces are too zoomed in (compared to the original face images) and thus, when I use the faces and alignments for training/conversion, the face coverage I have is too low. I already have a few hundred iters on training so I don't really want to redo the training with a higher face coverage if possible. Just using the original face images wouldn't work either due to a size mismatch (512x512 vs 256x256).

Thanks.

[torzdf]

The extraction zooming is standardized for all faceswap's processes.

I can't speak for what settings DFL uses.

[Dashon]

Thanks.

I just realised the issue is with DFL alignments being "smaller" (or showing less of the background behind the faces) as compared to faceswap's, instead of the issue being the extraction process itself, so I'd have to figure out a way to change that instead.