And before you say anything, yes I have tried swap model.
When I use the preview or convert function it just outputs the original video, I just wanna list my steps I'm doing to see if anything is wrong, I don't get error messages and I believe I've followed the guides to a tee, let me know if you need a log file.
First, I extract the frames from the video using the masks, aligners, and detectors, I selected. This leaves me with an alignment file and the frames.
Then I go to the preview tool and select my video file, trained model, and the alignment file I got from the previous step. When I click preview, no matter what maskers, etc. I choose it just shows the frames from the original video.
The same thing happens when I try to convert. I select the video file, alignment, model, and set all my settings and I convert it and it leaves me with just the original video.
Any help would be appreciated, but again, I have tried swap models many times to no avail.