Command Line Arguments

Complete reference for all ComfyUI command line arguments and flags

ComfyUI supports numerous command line arguments to customize server behavior, hardware configuration, memory management, and performance optimizations.

Running ComfyUI with Arguments

Pass arguments when launching ComfyUI:

python main.py --listen 0.0.0.0 --port 8188 --preview-method auto

Server Configuration

--listen · string · default: "127.0.0.1"

Specify the IP address to listen on. Use 0.0.0.0 to listen on all IPv4 addresses, or provide a comma-separated list.

# Listen on localhost only (default)
python main.py --listen 127.0.0.1

# Listen on all interfaces (IPv4 and IPv6)
python main.py --listen

# Listen on specific IPs
python main.py --listen 127.0.0.1,192.168.1.100

Using --listen without an argument defaults to 0.0.0.0,:: (all IPv4 and IPv6 addresses).

--port · integer · default: "8188"

Set the listen port for the web server.

python main.py --port 3000

--tls-keyfile · string

Path to TLS (SSL) key file. Enables HTTPS access. Requires --tls-certfile.

python main.py --tls-keyfile key.pem --tls-certfile cert.pem

--tls-certfile · string

Path to TLS (SSL) certificate file. Enables HTTPS access. Requires --tls-keyfile.

--enable-cors-header · string · default: "*"

Enable CORS (Cross-Origin Resource Sharing) with optional origin.

# Allow all origins
python main.py --enable-cors-header

# Allow specific origin
python main.py --enable-cors-header "https://example.com"

--max-upload-size · float · default: "100"

Set the maximum upload size in MB.

python main.py --max-upload-size 500

--auto-launch · boolean

Automatically launch ComfyUI in the default browser on startup.

python main.py --auto-launch

--disable-auto-launch · boolean

Disable auto-launching the browser (overrides --auto-launch).

--dont-print-server · boolean

Suppress server output messages.

--enable-compress-response-body · boolean

Enable response body compression to reduce bandwidth usage.

Directory Configuration

--base-directory · string

Set the ComfyUI base directory for models, custom_nodes, input, output, temp, and user directories.

python main.py --base-directory /path/to/comfyui

--output-directory · string

Set the output directory for generated images. Overrides --base-directory.

python main.py --output-directory /path/to/outputs

--input-directory · string

Set the input directory for source images. Overrides --base-directory.

python main.py --input-directory /path/to/inputs

--temp-directory · string

Set the temporary files directory. Overrides --base-directory.

python main.py --temp-directory /tmp/comfyui

--user-directory · string

Set the user directory with an absolute path. Overrides --base-directory.

python main.py --user-directory /path/to/user

--extra-model-paths-config · string

Load one or more extra_model_paths.yaml files. Can be specified multiple times.

python main.py --extra-model-paths-config /path/to/config1.yaml --extra-model-paths-config /path/to/config2.yaml

GPU and Device Configuration

--cuda-device · integer

Set the CUDA device ID to use. Makes all other devices invisible.

python main.py --cuda-device 0

--default-device · integer

Set the default device ID while keeping other devices visible.

python main.py --default-device 0

--directml · integer · default: "-1"

Use torch-directml for AMD/Intel GPUs on Windows.

# Use default DirectML device
python main.py --directml

# Use specific DirectML device
python main.py --directml 0

--oneapi-device-selector · string

Sets the oneAPI device selector for Intel GPUs.

python main.py --oneapi-device-selector "level_zero:0"

--disable-ipex-optimize · boolean

Disables ipex.optimize when loading models with Intel’s Extension for PyTorch.

--supports-fp8-compute · boolean

Force ComfyUI to act as if the device supports FP8 compute.

VRAM Management

--gpu-only · boolean

Store and run everything (text encoders, CLIP, VAE, etc.) on the GPU. Requires high VRAM.

python main.py --gpu-only

--highvram · boolean

Keep models in GPU memory after use instead of unloading to CPU. Requires ~12GB+ VRAM.

python main.py --highvram

--normalvram · boolean

Force normal VRAM usage mode (used if lowvram is automatically enabled).

python main.py --normalvram

--lowvram · boolean

Split the UNet model to use less VRAM. For GPUs with 4-8GB VRAM.

python main.py --lowvram

--novram · boolean

Extreme memory saving mode. Use when lowvram isn’t enough.

python main.py --novram

--cpu · boolean

Run everything on the CPU. Very slow but works without a GPU.

python main.py --cpu

--reserve-vram · float

Reserve amount of VRAM (in GB) for OS/other software.

python main.py --reserve-vram 2.0

--disable-smart-memory · boolean

Force aggressive offloading to RAM instead of keeping models in VRAM when possible.

--disable-dynamic-vram · boolean

Disable dynamic VRAM management and use estimate-based model loading.

--async-offload · integer · default: "2"

Use async weight offloading with specified number of streams. Enabled by default on NVIDIA.

# Use default 2 streams
python main.py --async-offload

# Use 4 streams
python main.py --async-offload 4

--disable-async-offload · boolean

Disable async weight offloading.

Precision and Data Types

Global Precision

--force-fp32 · boolean

Force FP32 precision globally. Use if your GPU has issues with FP16.

python main.py --force-fp32

--force-fp16 · boolean

Force FP16 precision globally.

python main.py --force-fp16

UNet/Diffusion Model Precision

--fp32-unet · boolean

Run the diffusion model in FP32 precision.

--fp16-unet · boolean

Run the diffusion model in FP16 precision.

--bf16-unet · boolean

Run the diffusion model in BF16 precision.

--fp64-unet · boolean

Run the diffusion model in FP64 precision (very slow, for debugging).

--fp8_e4m3fn-unet · boolean

Store UNet weights in FP8 E4M3FN format.

--fp8_e5m2-unet · boolean

Store UNet weights in FP8 E5M2 format.

--fp8_e8m0fnu-unet · boolean

Store UNet weights in FP8 E8M0FNU format.

VAE Precision

--fp16-vae · boolean

Run the VAE in FP16. May cause black images on some GPUs.

python main.py --fp16-vae

--fp32-vae · boolean

Run the VAE in full precision FP32. Use if you get black images.

python main.py --fp32-vae

--bf16-vae · boolean

Run the VAE in BF16 precision.

--cpu-vae · boolean

Run the VAE on the CPU instead of GPU. Slower but uses less VRAM.

python main.py --cpu-vae

Text Encoder Precision

--fp8_e4m3fn-text-enc · boolean

Store text encoder weights in FP8 (E4M3FN variant).

--fp8_e5m2-text-enc · boolean

Store text encoder weights in FP8 (E5M2 variant).

--fp16-text-enc · boolean

Store text encoder weights in FP16.

--fp32-text-enc · boolean

Store text encoder weights in FP32.

--bf16-text-enc · boolean

Store text encoder weights in BF16.

CUDA Configuration

--cuda-malloc · boolean

Enable cudaMallocAsync (enabled by default for PyTorch 2.0+).

--disable-cuda-malloc · boolean

Disable cudaMallocAsync. Use if you get CUDA errors.

python main.py --disable-cuda-malloc

--force-channels-last · boolean

Force channels-last memory format when inferencing models.

--force-non-blocking · boolean

Force non-blocking operations for all tensors. May improve performance on non-NVIDIA systems.

--disable-pinned-memory · boolean

Disable pinned memory usage.

Attention Mechanisms

--use-split-cross-attention · boolean

Use split cross attention optimization. Ignored when xformers is used.

--use-quad-cross-attention · boolean

Use sub-quadratic cross attention optimization. Ignored when xformers is used.

--use-pytorch-cross-attention · boolean

Use PyTorch 2.0+ native cross attention function.

python main.py --use-pytorch-cross-attention

--use-sage-attention · boolean

Use Sage Attention implementation.

--use-flash-attention · boolean

Use FlashAttention for faster attention computation.

--disable-xformers · boolean

Disable xformers optimization.

--force-upcast-attention · boolean

Force enable attention upcasting. Use if you get black images.

--dont-upcast-attention · boolean

Disable all attention upcasting. For debugging only.

Caching Strategies

--cache-classic · boolean

Use the old-style aggressive caching (default behavior).

python main.py --cache-classic

--cache-lru · integer · default: "0"

Use LRU caching with maximum N node results cached. May use more RAM/VRAM.

python main.py --cache-lru 10

--cache-none · boolean

Disable caching to reduce RAM/VRAM usage. Executes every node for each run.

python main.py --cache-none

--cache-ram · float · default: "4.0"

Use RAM pressure caching with specified headroom threshold (in GB). Removes large items when RAM is low.

# Use default 4GB threshold
python main.py --cache-ram

# Use 8GB threshold
python main.py --cache-ram 8.0

Preview Configuration

--preview-method · enum · default: "none"

Default preview method for sampler nodes. Options: none, auto, latent2rgb, taesd.

python main.py --preview-method auto

--preview-size · integer · default: "512"

Set the maximum preview size for sampler nodes.

python main.py --preview-size 768

File Loading Optimizations

--mmap-torch-files · boolean

Use memory mapping when loading .ckpt/.pt files.

python main.py --mmap-torch-files

--disable-mmap · boolean

Don’t use memory mapping when loading safetensors files.

--default-hashing-function · enum · default: "sha256"

Hash function for duplicate filename/contents comparison. Options: md5, sha1, sha256, sha512.

python main.py --default-hashing-function sha512

Performance Optimizations

--fast · string[]

Enable experimental optimizations that may reduce quality. Use without arguments to enable all, or specify individual features.

Available optimizations:

• fp16_accumulation - Use FP16 accumulation
• fp8_matrix_mult - Use FP8 matrix multiplication
• cublas_ops - Use cuBLAS operations
• autotune - Enable autotuning

# Enable all optimizations
python main.py --fast

# Enable specific optimizations
python main.py --fast fp16_accumulation fp8_matrix_mult

These are experimental features that may crash ComfyUI or reduce image quality.

--deterministic · boolean

Make PyTorch use slower deterministic algorithms when possible.

python main.py --deterministic

This may not make images fully deterministic in all cases.

Custom Nodes

--disable-all-custom-nodes · boolean

Disable loading all custom nodes.

python main.py --disable-all-custom-nodes

--whitelist-custom-nodes · string[]

Specify custom node folders to load even when --disable-all-custom-nodes is enabled.

python main.py --disable-all-custom-nodes --whitelist-custom-nodes "ComfyUI-Manager" "custom-node-2"

--disable-api-nodes · boolean

Disable loading all API nodes. Also prevents the frontend from communicating with the internet.

python main.py --disable-api-nodes

ComfyUI Manager

--enable-manager · boolean

Enable the ComfyUI-Manager feature.

python main.py --enable-manager

--disable-manager-ui · boolean

Disable only the ComfyUI-Manager UI and endpoints. Background tasks still operate. Requires --enable-manager.

python main.py --enable-manager --disable-manager-ui

--enable-manager-legacy-ui · boolean

Enable the legacy UI of ComfyUI-Manager. Requires --enable-manager.

python main.py --enable-manager --enable-manager-legacy-ui

Frontend Configuration

--front-end-version · string · default: "comfyanonymous/ComfyUI@latest"

Specify the frontend version to use. Format: [owner]/[repo]@[version]

# Use latest frontend
python main.py --front-end-version Comfy-Org/ComfyUI_frontend@latest

# Use specific version
python main.py --front-end-version Comfy-Org/ComfyUI_frontend@1.2.0

# Use legacy frontend
python main.py --front-end-version Comfy-Org/ComfyUI_legacy_frontend@latest

--front-end-root · string

Local filesystem path to frontend directory. Overrides --front-end-version.

python main.py --front-end-root /path/to/custom/frontend

Multi-User and Database

--multi-user · boolean

Enable per-user storage.

python main.py --multi-user

--database-url · string · default: "sqlite:///user/comfyui.db"

Specify the database URL.

# Use in-memory database
python main.py --database-url "sqlite:///:memory:"

# Use PostgreSQL
python main.py --database-url "postgresql://user:pass@localhost/comfyui"

--disable-assets-autoscan · boolean

Disable asset scanning on startup for database synchronization.

--comfy-api-base · string · default: "https://api.comfy.org"

Set the base URL for the ComfyUI API.

python main.py --comfy-api-base "https://custom-api.example.com"

Metadata and Output

--disable-metadata · boolean

Disable saving prompt metadata in output files.

python main.py --disable-metadata

Logging

--verbose · enum · default: "INFO"

Set the logging level. Options: DEBUG, INFO, WARNING, ERROR, CRITICAL.

python main.py --verbose DEBUG

--log-stdout · boolean

Send process output to stdout instead of stderr.

Development and Testing

--quick-test-for-ci · boolean

Quick test mode for continuous integration.

--windows-standalone-build · boolean

Enable features for Windows standalone build (auto-launch, etc.).

Example Configurations

Low VRAM Setup (4GB GPU)

python main.py --lowvram --fp16-vae --preview-method auto

High Performance (24GB+ GPU)

python main.py --highvram --gpu-only --preview-method taesd --fast

CPU Only

python main.py --cpu --preview-method auto

Remote Server

python main.py --listen 0.0.0.0 --port 8188 --preview-method auto

Development Mode

python main.py --verbose DEBUG --auto-launch --preview-method taesd

Shared Models with A1111

python main.py --extra-model-paths-config ./extra_model_paths.yaml --preview-method auto

Intel Arc GPU

python main.py --use-pytorch-cross-attention --preview-method auto

AMD ROCm

python main.py --use-pytorch-cross-attention --preview-method auto