Options

Options

• --port: Set the listen port
• --share: Set whether to share on Gradio.
• --auth: Set credentials username/password. Example: --auth=root/hunter2
• --listen: Set the listen interface
• --nobrowser: Do not launch in browser.
• --gpu-device-id: Select GPU (equivalent to CUDA_VISIBLE_DEVICES=x)
• --offline: Skip the git and pip checks at startup.

ComfyUI

RuinedFooocus try to support some of the options from ComfyUI.

• --directml: Use torch-directml. (broken, if you have an AMD card and want to help, please join the Discord)
• --gpu-only: Store and run everything (text encoders/CLIP models, etc... on the GPU).
• --highvram: By default models will be unloaded to CPU memory after being used. This option keeps them in GPU memory.
• --normalvram: Used to force normal vram use if lowvram gets automatically enabled.
• --lowvram: Split the unet in parts to use less vram.
• --novram: When lowvram isn't enough.
• --cpu: To use the CPU for everything (slow).
• --reserve-vram: Set the amount of vram in GB you want to reserve for use by your OS/other software. By default some amount is reserved depending on your OS.
• --cpu-vae: Run the VAE on the CPU.