CLI

FlashDreams exposes a unified command line entry point: flashdreams-run.

Core commands

List all available runner slugs:

uv run flashdreams-run --help

Inspect one runner’s full options:

uv run flashdreams-run self-forcing-wan2.1-t2v-1.3b-taehv --help

Run a single-GPU inference:

uv run flashdreams-run self-forcing-wan2.1-t2v-1.3b-taehv --total-blocks 7

Run a multi-GPU inference:

uv run torchrun --nproc_per_node=4 --no-python flashdreams-run \
    self-forcing-wan2.1-t2v-1.3b-taehv --total-blocks 7

Resolve config only (no model instantiation):

uv run flashdreams-run --no-instantiate self-forcing-wan2.1-t2v-1.3b-taehv

See also