Specify the devices used for processing.
Argument: --execution-device-ids
Default: 0
Example: --execution-device-id 0 1
Inference using different providers.
Argument: --execution-providers
Default: Auto
Choices:
cpu
coreml
cuda
directml
migraphx
rocm
tensorrt
Example: --execution-providers cuda
Specify the amount of parallel threads while processing.
Argument --execution-thread-count
Default: 4
Range: 1 to 32 at 1
Example: --execution-thread-count 16
Modify the facefusion.ini file to override the defaults.
[execution]
execution_device_ids = 0 1
execution_providers = cuda
execution_thread_count = 16