Deep-Live-Cam icon indicating copy to clipboard operation
Deep-Live-Cam copied to clipboard

Recommended settings

Open wasgehthierab opened this issue 1 year ago • 2 comments

I would like to know which settings are the best to use the optimal power of my computer. I have a m1 pro and it has 8-core CPU with 6 performance cores and 2 efficiency cores, a 14-core GPU and 16-core Neural Engine... so which of these cores is used by deep-live-cam? What would be the optimal settings for the options?

  --video-encoder {libx264,libx265,libvpx-vp9}             adjust output video encoder
  --video-quality [0-51]                                   adjust output video quality
  --max-memory MAX_MEMORY                                  maximum amount of RAM in GB
  --execution-provider {cpu} [{cpu} ...]                   available execution provider (choices: cpu, ...)
  --execution-threads EXECUTION_THREADS                    number of execution threads

I installed the dependencies for Apple Silicon and run deep-live-com with python run.py --execution-provider coreml

Thanks for the help and the awesome project!

wasgehthierab avatar Aug 14 '24 18:08 wasgehthierab

I could only get the max memory up to 7 even though my machine has 16. It doesn't allow me to go further. So, you could try it.

For a better performance, please download inswapper_216.onnx (no fp16) from huggingface, rename it to inswapper_216.fp16.onnx, and replace this file with the one in the modules folder.

Also, instead of installing onnxruntime 1.13.1, try 1.16.3:

pip uninstall onnxruntime onnxruntime-silicon
pip install onnxruntime-silicon==1.13.1

After these steps, you should be getting +10 fps, and no temperature issues. It still does not fully utilize the GPU cores though. Hoping to get a fix for it.

e-basaran avatar Aug 15 '24 09:08 e-basaran

Retha can u give u discord to helpme please? my discord is bruxamadooeste add me

lulu3243 avatar Aug 17 '24 05:08 lulu3243