Performance Issue on macOS

[ViperGash]

I am running on a macOS M4 with 128GB RAM. Without the enhance option, the performance is relatively smooth. Once I enable the enhance mode, the frame rate drops to approximately 0.2 - 0.3 FPS.

I tried --execution-threads 20 --max-memory 8, but it seems report an error:

Traceback (most recent call last):
  File "/Users/y/Downloads/Owned Tools/Deep-Live-Cam/run.py", line 6, in <module>
    core.run()
  File "/Users/y/Downloads/Owned Tools/Deep-Live-Cam/modules/core.py", line 250, in run
    limit_resources()
  File "/Users/y/Downloads/Owned Tools/Deep-Live-Cam/modules/core.py", line 151, in limit_resources
    resource.setrlimit(resource.RLIMIT_DATA, (memory, memory))
OverflowError: Python int too large to convert to C long

So I set --execution-threads to 20 and --max-memory to 7, but it doesn’t seem to improve performance.

Any suggenstion should I do to improve it?

[RishonLi]

You can try modifying face_enhancer.py face_enhancer.py#L52
by appending mps

            mps_device = None
            if torch.backends.mps.is_available():
                mps_device = torch.device("mps")
            FACE_ENHANCER = gfpgan.GFPGANer(model_path=model_path, upscale=1, device=mps_device)  # type: ignore[attr-defined]

I hope it's helpful to you