stable-diffusion.cpp
stable-diffusion.cpp copied to clipboard
Support for PhotoMaker Version 2
This PR added support for PhotoMaker V2 (PMV2).
PMV2 requires/adds a face detection step via insightface. I couldn't find a C++ lib to do equivalent in SD. (There is a c++ SDK called InspireFace but it is pretty heavy and I don't think SD wants to add it as dependency). So a workaround is to add an additional manual step: a python script was created to do face detection and generate resultant id_embedding. This id_embedding is then fed into SD along with input images.
See more in updated README.
SD PhotoMaker V2 | Official Pytorch PhotoMaker V2 |
---|---|