Execution

CLI Arguments

Execution Providers

Accelerate the model inference using different providers.

Argument: --execution-providers

Default: cpu

Example: --execution-providers cuda

Execution Thread Count

Specify the amount of parallel threads while processing.

Argument --execution-thread-count

Default: 1

Range: 1-128 at 1

Example: --execution-thread-count 32

Execution Queue Count

Specify the amount of frames each thread is processing.

Argument --execution-queue-count

Default: 1

Range: 1-32 at 1

Example: --execution-queue-count 2

Default Overrides

Modify the facefusion.ini file to override the defaults.

[execution]
execution_providers = cuda
execution_thread_count = 32
execution_queue_count = 2

Last updated