> ## Documentation Index
> Fetch the complete documentation index at: https://docs.omnichar.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Omnichar Studio command-line options

> Flags and INLINE_* environment variables for webui.sh and webui.bat: port, LAN access, model folder, low-VRAM mode, multi-GPU and PyTorch index.

`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

```bash theme={null}
./webui.sh --listen
```

> [!WARNING]
>
> `--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.

## Share characters with ComfyUI

Set `INLINE_CHARACTERS_DIR` to the same folder the [ComfyUI node](/comfyui/install#where-characters-live) 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`:

```bash theme={null}
uv pip install -e ".[runtime,parallel]"
./webui.sh --multi-gpu
```


## Related topics

- [Install Omnichar Studio](/app/install.md)
- [Omnichar Studio overview](/app/overview.md)
- [Supported models in Omnichar Studio](/app/models.md)
- [About Omnichar](/index.md)
- [Omnichar Cloud overview](/cloud/overview.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.