Omnichar Studio command-line options - Omnichar

webui.sh (macOS and Linux) and webui.bat (Windows) turn these flags into the engine’s INLINE_* environment variables. core/main.py takes the same flags. Run --help for the full list.

Flag	Env var	What it does
`--listen`	`INLINE_HOST=0.0.0.0`	Bind all interfaces so other machines can reach it
`--port N`	`INLINE_PORT`	Port to serve on (default 8848)
`--models-dir PATH`	`INLINE_MODELS_DIR`	Where model files are scanned from (default `./models`)
`--data-dir PATH`	`INLINE_DATA_DIR`	Where runs and takes are written
`--lowvram`	`INLINE_PROFILE=lowvram`	Tight-VRAM profile (tiling, slicing, int8)
`--cpu`	`INLINE_PROFILE=cpu`	Force CPU generation
`--vram-budget GB`	`INLINE_VRAM_BUDGET_GB`	Treat the GPU as having GB of usable VRAM
`--multi-gpu [SPEC]`	`INLINE_PARALLEL`	Split one image’s denoise across GPUs; on by default with 2+
`--torch-index WHICH`	`INLINE_TORCH_INDEX`	With `--install`, override the PyTorch wheel index
`--print-torch-index`	n/a	Print the GPU probe and chosen index, then exit
`--extra NAME`	n/a	Add an install extra: `runtime`, `server`, `training`, `all`
`--recreate`	n/a	Rebuild `.venv` from scratch
`--dev` / `--rebuild`	n/a	Live-reload dev loop / force a fresh UI build

The INLINE_* names come from the engine, Inline Core, and stay as they are so existing launch scripts keep working.

Reach it from another machine

./webui.sh --listen

--listen exposes the app and its API to your whole network with no login. On a machine with a public IP, put it behind a firewall rule or a tunnel.

Set INLINE_CHARACTERS_DIR to the same folder the ComfyUI node reads, and both tools see the same .char files.

Multiple GPUs

With two or more GPUs, Inline Core can split one image’s denoise loop across them so a single render finishes sooner. That’s different from running one image per GPU. Install the extra, then start with --multi-gpu:

uv pip install -e ".[runtime,parallel]"
./webui.sh --multi-gpu