Files
ComfyUI/comfy/cli_args.py
rattus 5aa5ccc9e0 Multi-threaded load of models from disk (big load time speedups & Offload to disk) (CORE-43,CORE-152,CORE-164,CORE-165,CORE-117) (#13802)
* model_management: disable non-dynamic smart memory

Disable smart memory outright for non dynamic models.

This is a minor step towards deprecation of --disable-dynamic-vram
and the legacy ModelPatcher.

This is needed for estimate-free model development, where new models
can opt-out of supplying a memory estimate and not have to worry
about hard VRAM allocations due to legacy non-dynamic model patchers

This is also a general stability increase for a lot of stray use cases
where estimates may still be off and going forward we are not going
to accurately maintain such estimates.

* pinned_memory: implement with aimdo growable buffer

Use a single growable buffer so we can do threaded pre-warming on
pinned memory.

* mm: use aimdo to do transfer from disk to pin

Aimdo implements a faster threaded loader.

* Add stream host pin buffer for AIMDO casts

Introduce per-offload-stream HostBuffer reuse for pinned staging,
include it in cast buffer reset synchronization.

Defer actual casts that go via this pin path to a separate pass
such that the buffer can be allocated monolithically (to avoid
cudaHostRegister thrash).

* remove old pin path

* Implement JIT pinned memory pressure

Replace the predictive pin pressure mechanism with JIT PIN memory
pressure.

* LowVRAMPatch: change to two-phase visit

* lora: re-implement as inplace swiss-army-knife operation

* prepare for multiple pin sets

* implement pinned loras

* requirements: comfy-aimdo 0.4.0

* ops: remove unused arg

This was defeatured in aimdo iteration

* ops: sync the CPU with only the offload stream activity

This was syncing with the offload stream which itself is synced with the
compute stream, so this was syncing CPU with compute transitively. Define
the event to sync it more gently.

* pins: implement freeing intermediate for pinned memory

Pinning is more important than inactive intermediates and the stream
pin buffer is more important than even active intermediates.

* execution: implement pin eviction on RAM presure

Add back proper pin freeing on RAM pressure

* implement pin registration swaps

Uncap the windows pins from 50% by extending the pool and have a pressure
mechanism to move the pin reservations om demand.

This unfortunately implies a GPU sync to do the freeing so significant
hysterisis needs to be added to consolidate these pressure events.

* cli_args/execution: Implement lower background cache-ram threshold

Limit the amount of RAM background intermediates can use, so that
switching workflows doesn't degrade performance too much.

* make default

* bump aimdo

* model-patcher: force-cast tiny weights

Flux 2 gets crazy stalls due to a mix of tiny and giant weights
creating lopsided steam buffer rotations which creates stalls.

* ops: refactor in prep for chunking

* mm: delegate pin-on-the-way to aimdo

Aimdo is able to chunk and slice this on the way for better CPU->GPU
overlap. The main advantage is the ability to shorten the bus contention
window between previous weight transfer and the next weights vbar
fault.

* bump aimdo

* pinning updates

* specify hostbuf max allocation size

There a signs of virtual memory exhaustion on some linux systems when
throwing 128GB for every little piece. Pass the actual to save aimdo
from over-estimates

* tests: update execution tests for caching

The default caching changed to ram-cache so update these tests
accordingly.

Remove the LRU 0 test as this also falls through to RAM cache.
2026-05-20 17:03:58 -07:00

273 lines
18 KiB
Python

import argparse
import enum
import os
import comfy.options
class EnumAction(argparse.Action):
"""
Argparse action for handling Enums
"""
def __init__(self, **kwargs):
# Pop off the type value
enum_type = kwargs.pop("type", None)
# Ensure an Enum subclass is provided
if enum_type is None:
raise ValueError("type must be assigned an Enum when using EnumAction")
if not issubclass(enum_type, enum.Enum):
raise TypeError("type must be an Enum when using EnumAction")
# Generate choices from the Enum
choices = tuple(e.value for e in enum_type)
kwargs.setdefault("choices", choices)
kwargs.setdefault("metavar", f"[{','.join(list(choices))}]")
super(EnumAction, self).__init__(**kwargs)
self._enum = enum_type
def __call__(self, parser, namespace, values, option_string=None):
# Convert value back into an Enum
value = self._enum(values)
setattr(namespace, self.dest, value)
parser = argparse.ArgumentParser()
parser.add_argument("--listen", type=str, default="127.0.0.1", metavar="IP", nargs="?", const="0.0.0.0,::", help="Specify the IP address to listen on (default: 127.0.0.1). You can give a list of ip addresses by separating them with a comma like: 127.2.2.2,127.3.3.3 If --listen is provided without an argument, it defaults to 0.0.0.0,:: (listens on all ipv4 and ipv6)")
parser.add_argument("--port", type=int, default=8188, help="Set the listen port.")
parser.add_argument("--tls-keyfile", type=str, help="Path to TLS (SSL) key file. Enables TLS, makes app accessible at https://... requires --tls-certfile to function")
parser.add_argument("--tls-certfile", type=str, help="Path to TLS (SSL) certificate file. Enables TLS, makes app accessible at https://... requires --tls-keyfile to function")
parser.add_argument("--enable-cors-header", type=str, default=None, metavar="ORIGIN", nargs="?", const="*", help="Enable CORS (Cross-Origin Resource Sharing) with optional origin or allow all with default '*'.")
parser.add_argument("--max-upload-size", type=float, default=100, help="Set the maximum upload size in MB.")
parser.add_argument("--base-directory", type=str, default=None, help="Set the ComfyUI base directory for models, custom_nodes, input, output, temp, and user directories.")
parser.add_argument("--extra-model-paths-config", type=str, default=None, metavar="PATH", nargs='+', action='append', help="Load one or more extra_model_paths.yaml files.")
parser.add_argument("--output-directory", type=str, default=None, help="Set the ComfyUI output directory. Overrides --base-directory.")
parser.add_argument("--temp-directory", type=str, default=None, help="Set the ComfyUI temp directory (default is in the ComfyUI directory). Overrides --base-directory.")
parser.add_argument("--input-directory", type=str, default=None, help="Set the ComfyUI input directory. Overrides --base-directory.")
parser.add_argument("--auto-launch", action="store_true", help="Automatically launch ComfyUI in the default browser.")
parser.add_argument("--disable-auto-launch", action="store_true", help="Disable auto launching the browser.")
parser.add_argument("--cuda-device", type=int, default=None, metavar="DEVICE_ID", help="Set the id of the cuda device this instance will use. All other devices will not be visible.")
parser.add_argument("--default-device", type=int, default=None, metavar="DEFAULT_DEVICE_ID", help="Set the id of the default device, all other devices will stay visible.")
cm_group = parser.add_mutually_exclusive_group()
cm_group.add_argument("--cuda-malloc", action="store_true", help="Enable cudaMallocAsync (enabled by default for torch 2.0 and up).")
cm_group.add_argument("--disable-cuda-malloc", action="store_true", help="Disable cudaMallocAsync.")
fp_group = parser.add_mutually_exclusive_group()
fp_group.add_argument("--force-fp32", action="store_true", help="Force fp32 (If this makes your GPU work better please report it).")
fp_group.add_argument("--force-fp16", action="store_true", help="Force fp16.")
fpunet_group = parser.add_mutually_exclusive_group()
fpunet_group.add_argument("--fp32-unet", action="store_true", help="Run the diffusion model in fp32.")
fpunet_group.add_argument("--fp64-unet", action="store_true", help="Run the diffusion model in fp64.")
fpunet_group.add_argument("--bf16-unet", action="store_true", help="Run the diffusion model in bf16.")
fpunet_group.add_argument("--fp16-unet", action="store_true", help="Run the diffusion model in fp16")
fpunet_group.add_argument("--fp8_e4m3fn-unet", action="store_true", help="Store unet weights in fp8_e4m3fn.")
fpunet_group.add_argument("--fp8_e5m2-unet", action="store_true", help="Store unet weights in fp8_e5m2.")
fpunet_group.add_argument("--fp8_e8m0fnu-unet", action="store_true", help="Store unet weights in fp8_e8m0fnu.")
fpvae_group = parser.add_mutually_exclusive_group()
fpvae_group.add_argument("--fp16-vae", action="store_true", help="Run the VAE in fp16, might cause black images.")
fpvae_group.add_argument("--fp32-vae", action="store_true", help="Run the VAE in full precision fp32.")
fpvae_group.add_argument("--bf16-vae", action="store_true", help="Run the VAE in bf16.")
parser.add_argument("--cpu-vae", action="store_true", help="Run the VAE on the CPU.")
fpte_group = parser.add_mutually_exclusive_group()
fpte_group.add_argument("--fp8_e4m3fn-text-enc", action="store_true", help="Store text encoder weights in fp8 (e4m3fn variant).")
fpte_group.add_argument("--fp8_e5m2-text-enc", action="store_true", help="Store text encoder weights in fp8 (e5m2 variant).")
fpte_group.add_argument("--fp16-text-enc", action="store_true", help="Store text encoder weights in fp16.")
fpte_group.add_argument("--fp32-text-enc", action="store_true", help="Store text encoder weights in fp32.")
fpte_group.add_argument("--bf16-text-enc", action="store_true", help="Store text encoder weights in bf16.")
parser.add_argument("--fp16-intermediates", action="store_true", help="Experimental: Use fp16 for intermediate tensors between nodes instead of fp32.")
parser.add_argument("--force-channels-last", action="store_true", help="Force channels last format when inferencing the models.")
parser.add_argument("--directml", type=int, nargs="?", metavar="DIRECTML_DEVICE", const=-1, help="Use torch-directml.")
parser.add_argument("--oneapi-device-selector", type=str, default=None, metavar="SELECTOR_STRING", help="Sets the oneAPI device(s) this instance will use.")
parser.add_argument("--supports-fp8-compute", action="store_true", help="ComfyUI will act like if the device supports fp8 compute.")
parser.add_argument("--enable-triton-backend", action="store_true", help="ComfyUI will enable the use of Triton backend in comfy-kitchen. Is disabled at launch by default.")
class LatentPreviewMethod(enum.Enum):
NoPreviews = "none"
Auto = "auto"
Latent2RGB = "latent2rgb"
TAESD = "taesd"
@classmethod
def from_string(cls, value: str):
for member in cls:
if member.value == value:
return member
return None
parser.add_argument("--preview-method", type=LatentPreviewMethod, default=LatentPreviewMethod.NoPreviews, help="Default preview method for sampler nodes.", action=EnumAction)
parser.add_argument("--preview-size", type=int, default=512, help="Sets the maximum preview size for sampler nodes.")
cache_group = parser.add_mutually_exclusive_group()
cache_group.add_argument("--cache-ram", nargs='*', type=float, default=[], metavar="GB", help="Use RAM pressure caching with the specified headroom thresholds. This is the default caching mode. The first value sets the active-cache threshold; the optional second value sets the inactive-cache/pin threshold. Defaults when no values are provided: active 25%% of system RAM (min 4GB, max 32GB), inactive 75%% of system RAM (min 12GB, max 96GB).")
cache_group.add_argument("--cache-classic", action="store_true", help="Use the old style (aggressive) caching.")
cache_group.add_argument("--cache-lru", type=int, default=0, help="Use LRU caching with a maximum of N node results cached. May use more RAM/VRAM.")
cache_group.add_argument("--cache-none", action="store_true", help="Reduced RAM/VRAM usage at the expense of executing every node for each run.")
attn_group = parser.add_mutually_exclusive_group()
attn_group.add_argument("--use-split-cross-attention", action="store_true", help="Use the split cross attention optimization. Ignored when xformers is used.")
attn_group.add_argument("--use-quad-cross-attention", action="store_true", help="Use the sub-quadratic cross attention optimization . Ignored when xformers is used.")
attn_group.add_argument("--use-pytorch-cross-attention", action="store_true", help="Use the new pytorch 2.0 cross attention function.")
attn_group.add_argument("--use-sage-attention", action="store_true", help="Use sage attention.")
attn_group.add_argument("--use-flash-attention", action="store_true", help="Use FlashAttention.")
parser.add_argument("--disable-xformers", action="store_true", help="Disable xformers.")
upcast = parser.add_mutually_exclusive_group()
upcast.add_argument("--force-upcast-attention", action="store_true", help="Force enable attention upcasting, please report if it fixes black images.")
upcast.add_argument("--dont-upcast-attention", action="store_true", help="Disable all upcasting of attention. Should be unnecessary except for debugging.")
parser.add_argument("--enable-manager", action="store_true", help="Enable the ComfyUI-Manager feature.")
manager_group = parser.add_mutually_exclusive_group()
manager_group.add_argument("--disable-manager-ui", action="store_true", help="Disables only the ComfyUI-Manager UI and endpoints. Scheduled installations and similar background tasks will still operate.")
manager_group.add_argument("--enable-manager-legacy-ui", action="store_true", help="Enables the legacy UI of ComfyUI-Manager")
vram_group = parser.add_mutually_exclusive_group()
vram_group.add_argument("--gpu-only", action="store_true", help="Store and run everything (text encoders/CLIP models, etc... on the GPU).")
vram_group.add_argument("--highvram", action="store_true", help="By default models will be unloaded to CPU memory after being used. This option keeps them in GPU memory.")
vram_group.add_argument("--lowvram", action="store_true", help="Doesn't do anything if dynamic vram is enabled. If dynamic vram isn't being used this option makes the text encoders run on the CPU.")
vram_group.add_argument("--novram", action="store_true", help="When lowvram isn't enough.")
vram_group.add_argument("--cpu", action="store_true", help="To use the CPU for everything (slow).")
parser.add_argument("--reserve-vram", type=float, default=None, help="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.")
parser.add_argument("--async-offload", nargs='?', const=2, type=int, default=None, metavar="NUM_STREAMS", help="Use async weight offloading. An optional argument controls the amount of offload streams. Default is 2. Enabled by default on Nvidia.")
parser.add_argument("--disable-async-offload", action="store_true", help="Disable async weight offloading.")
parser.add_argument("--disable-dynamic-vram", action="store_true", help="Disable dynamic VRAM and use estimate based model loading.")
parser.add_argument("--enable-dynamic-vram", action="store_true", help="Enable dynamic VRAM on systems where it's not enabled by default.")
parser.add_argument("--force-non-blocking", action="store_true", help="Force ComfyUI to use non-blocking operations for all applicable tensors. This may improve performance on some non-Nvidia systems but can cause issues with some workflows.")
parser.add_argument("--default-hashing-function", type=str, choices=['md5', 'sha1', 'sha256', 'sha512'], default='sha256', help="Allows you to choose the hash function to use for duplicate filename / contents comparison. Default is sha256.")
parser.add_argument("--disable-smart-memory", action="store_true", help="Force ComfyUI to agressively offload to regular ram instead of keeping models in vram when it can.")
parser.add_argument("--deterministic", action="store_true", help="Make pytorch use slower deterministic algorithms when it can. Note that this might not make images deterministic in all cases.")
class PerformanceFeature(enum.Enum):
Fp16Accumulation = "fp16_accumulation"
Fp8MatrixMultiplication = "fp8_matrix_mult"
CublasOps = "cublas_ops"
AutoTune = "autotune"
parser.add_argument("--fast", nargs="*", type=PerformanceFeature, help="Enable some untested and potentially quality deteriorating optimizations. This is used to test new features so using it might crash your comfyui. --fast with no arguments enables everything. You can pass a list specific optimizations if you only want to enable specific ones. Current valid optimizations: {}".format(" ".join(map(lambda c: c.value, PerformanceFeature))))
parser.add_argument("--disable-pinned-memory", action="store_true", help="Disable pinned memory use.")
parser.add_argument("--mmap-torch-files", action="store_true", help="Use mmap when loading ckpt/pt files.")
parser.add_argument("--disable-mmap", action="store_true", help="Don't use mmap when loading safetensors.")
parser.add_argument("--dont-print-server", action="store_true", help="Don't print server output.")
parser.add_argument("--quick-test-for-ci", action="store_true", help="Quick test for CI.")
parser.add_argument("--windows-standalone-build", action="store_true", help="Windows standalone build: Enable convenient things that most people using the standalone windows build will probably enjoy (like auto opening the page on startup).")
parser.add_argument("--disable-metadata", action="store_true", help="Disable saving prompt metadata in files.")
parser.add_argument("--disable-all-custom-nodes", action="store_true", help="Disable loading all custom nodes.")
parser.add_argument("--whitelist-custom-nodes", type=str, nargs='+', default=[], help="Specify custom node folders to load even when --disable-all-custom-nodes is enabled.")
parser.add_argument("--disable-api-nodes", action="store_true", help="Disable loading all api nodes. Also prevents the frontend from communicating with the internet.")
parser.add_argument("--multi-user", action="store_true", help="Enables per-user storage.")
parser.add_argument("--verbose", default='INFO', const='DEBUG', nargs="?", choices=['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'], help='Set the logging level')
parser.add_argument("--log-stdout", action="store_true", help="Send normal process output to stdout instead of stderr (default).")
# The default built-in provider hosted under web/
DEFAULT_VERSION_STRING = "comfyanonymous/ComfyUI@latest"
parser.add_argument(
"--front-end-version",
type=str,
default=DEFAULT_VERSION_STRING,
help="""
Specifies the version of the frontend to be used. This command needs internet connectivity to query and
download available frontend implementations from GitHub releases.
The version string should be in the format of:
[repoOwner]/[repoName]@[version]
where version is one of: "latest" or a valid version number (e.g. "1.0.0")
""",
)
def is_valid_directory(path: str) -> str:
"""Validate if the given path is a directory, and check permissions."""
if not os.path.exists(path):
raise argparse.ArgumentTypeError(f"The path '{path}' does not exist.")
if not os.path.isdir(path):
raise argparse.ArgumentTypeError(f"'{path}' is not a directory.")
if not os.access(path, os.R_OK):
raise argparse.ArgumentTypeError(f"You do not have read permissions for '{path}'.")
return path
parser.add_argument(
"--front-end-root",
type=is_valid_directory,
default=None,
help="The local filesystem path to the directory where the frontend is located. Overrides --front-end-version.",
)
parser.add_argument("--user-directory", type=is_valid_directory, default=None, help="Set the ComfyUI user directory with an absolute path. Overrides --base-directory.")
parser.add_argument("--enable-compress-response-body", action="store_true", help="Enable compressing response body.")
parser.add_argument(
"--comfy-api-base",
type=str,
default="https://api.comfy.org",
help="Set the base URL for the ComfyUI API. (default: https://api.comfy.org)",
)
database_default_path = os.path.abspath(
os.path.join(os.path.dirname(__file__), "..", "user", "comfyui.db")
)
parser.add_argument("--database-url", type=str, default=f"sqlite:///{database_default_path}", help="Specify the database URL, e.g. for an in-memory database you can use 'sqlite:///:memory:'.")
parser.add_argument("--enable-assets", action="store_true", help="Enable the assets system (API routes, database synchronization, and background scanning).")
parser.add_argument("--feature-flag", type=str, action='append', default=[], metavar="KEY[=VALUE]", help="Set a server feature flag. Use KEY=VALUE to set an explicit value, or bare KEY to set it to true. Can be specified multiple times. Boolean values (true/false) and numbers are auto-converted. Examples: --feature-flag show_signin_button=true or --feature-flag show_signin_button")
parser.add_argument("--list-feature-flags", action="store_true", help="Print the registry of known CLI-settable feature flags as JSON and exit.")
if comfy.options.args_parsing:
args = parser.parse_args()
else:
args = parser.parse_args([])
if args.cache_ram is not None and len(args.cache_ram) > 2:
parser.error("--cache-ram accepts at most two values: active GB and inactive GB")
if args.windows_standalone_build:
args.auto_launch = True
if args.disable_auto_launch:
args.auto_launch = False
if args.force_fp16:
args.fp16_unet = True
# '--fast' is not provided, use an empty set
if args.fast is None:
args.fast = set()
# '--fast' is provided with an empty list, enable all optimizations
elif args.fast == []:
args.fast = set(PerformanceFeature)
# '--fast' is provided with a list of performance features, use that list
else:
args.fast = set(args.fast)
def enables_dynamic_vram():
if args.enable_dynamic_vram:
return True
return not args.disable_dynamic_vram and not args.highvram and not args.gpu_only and not args.novram and not args.cpu