Files
ComfyUI/comfy/cli_args.py

280 lines
19 KiB
Python
Raw Normal View History

import argparse
2023-06-05 13:19:02 -05:00
import enum
import os
import comfy.options
2023-06-05 13:19:02 -05:00
2023-06-05 13:19:02 -05:00
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.")
2023-05-06 16:59:40 -04:00
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=str, default=None, metavar="DEVICE_ID", help="Set the ids of cuda devices this instance will use, as a comma-separated list (e.g. '0' or '0,1'). All other devices will not be visible.")
2025-07-23 11:20:49 -07:00
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.")
2025-04-01 23:18:53 +05:30
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.")
2023-06-05 18:59:10 -05:00
class LatentPreviewMethod(enum.Enum):
NoPreviews = "none"
2023-06-05 18:59:10 -05:00
Auto = "auto"
2023-06-05 18:39:56 -05:00
Latent2RGB = "latent2rgb"
2023-06-05 13:19:02 -05:00
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)
2023-06-05 13:19:02 -05:00
parser.add_argument("--preview-size", type=int, default=512, help="Sets the maximum preview size for sampler nodes.")
Execution Model Inversion (#2666) * Execution Model Inversion This PR inverts the execution model -- from recursively calling nodes to using a topological sort of the nodes. This change allows for modification of the node graph during execution. This allows for two major advantages: 1. The implementation of lazy evaluation in nodes. For example, if a "Mix Images" node has a mix factor of exactly 0.0, the second image input doesn't even need to be evaluated (and visa-versa if the mix factor is 1.0). 2. Dynamic expansion of nodes. This allows for the creation of dynamic "node groups". Specifically, custom nodes can return subgraphs that replace the original node in the graph. This is an incredibly powerful concept. Using this functionality, it was easy to implement: a. Components (a.k.a. node groups) b. Flow control (i.e. while loops) via tail recursion c. All-in-one nodes that replicate the WebUI functionality d. and more All of those were able to be implemented entirely via custom nodes, so those features are *not* a part of this PR. (There are some front-end changes that should occur before that functionality is made widely available, particularly around variant sockets.) The custom nodes associated with this PR can be found at: https://github.com/BadCafeCode/execution-inversion-demo-comfyui Note that some of them require that variant socket types ("*") be enabled. * Allow `input_info` to be of type `None` * Handle errors (like OOM) more gracefully * Add a command-line argument to enable variants This allows the use of nodes that have sockets of type '*' without applying a patch to the code. * Fix an overly aggressive assertion. This could happen when attempting to evaluate `IS_CHANGED` for a node during the creation of the cache (in order to create the cache key). * Fix Pyright warnings * Add execution model unit tests * Fix issue with unused literals Behavior should now match the master branch with regard to undeclared inputs. Undeclared inputs that are socket connections will be used while undeclared inputs that are literals will be ignored. * Make custom VALIDATE_INPUTS skip normal validation Additionally, if `VALIDATE_INPUTS` takes an argument named `input_types`, that variable will be a dictionary of the socket type of all incoming connections. If that argument exists, normal socket type validation will not occur. This removes the last hurdle for enabling variant types entirely from custom nodes, so I've removed that command-line option. I've added appropriate unit tests for these changes. * Fix example in unit test This wouldn't have caused any issues in the unit test, but it would have bugged the UI if someone copy+pasted it into their own node pack. * Use fstrings instead of '%' formatting syntax * Use custom exception types. * Display an error for dependency cycles Previously, dependency cycles that were created during node expansion would cause the application to quit (due to an uncaught exception). Now, we'll throw a proper error to the UI. We also make an attempt to 'blame' the most relevant node in the UI. * Add docs on when ExecutionBlocker should be used * Remove unused functionality * Rename ExecutionResult.SLEEPING to PENDING * Remove superfluous function parameter * Pass None for uneval inputs instead of default This applies to `VALIDATE_INPUTS`, `check_lazy_status`, and lazy values in evaluation functions. * Add a test for mixed node expansion This test ensures that a node that returns a combination of expanded subgraphs and literal values functions correctly. * Raise exception for bad get_node calls. * Minor refactor of IsChangedCache.get * Refactor `map_node_over_list` function * Fix ui output for duplicated nodes * Add documentation on `check_lazy_status` * Add file for execution model unit tests * Clean up Javascript code as per review * Improve documentation Converted some comments to docstrings as per review * Add a new unit test for mixed lazy results This test validates that when an output list is fed to a lazy node, the node will properly evaluate previous nodes that are needed by any inputs to the lazy node. No code in the execution model has been changed. The test already passes. * Allow kwargs in VALIDATE_INPUTS functions When kwargs are used, validation is skipped for all inputs as if they had been mentioned explicitly. * List cached nodes in `execution_cached` message This was previously just bugged in this PR.
2024-08-15 08:21:11 -07:00
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 10%% of system RAM (min 2GB, max 10GB), inactive 100%% of system RAM (max 96GB).")
Execution Model Inversion (#2666) * Execution Model Inversion This PR inverts the execution model -- from recursively calling nodes to using a topological sort of the nodes. This change allows for modification of the node graph during execution. This allows for two major advantages: 1. The implementation of lazy evaluation in nodes. For example, if a "Mix Images" node has a mix factor of exactly 0.0, the second image input doesn't even need to be evaluated (and visa-versa if the mix factor is 1.0). 2. Dynamic expansion of nodes. This allows for the creation of dynamic "node groups". Specifically, custom nodes can return subgraphs that replace the original node in the graph. This is an incredibly powerful concept. Using this functionality, it was easy to implement: a. Components (a.k.a. node groups) b. Flow control (i.e. while loops) via tail recursion c. All-in-one nodes that replicate the WebUI functionality d. and more All of those were able to be implemented entirely via custom nodes, so those features are *not* a part of this PR. (There are some front-end changes that should occur before that functionality is made widely available, particularly around variant sockets.) The custom nodes associated with this PR can be found at: https://github.com/BadCafeCode/execution-inversion-demo-comfyui Note that some of them require that variant socket types ("*") be enabled. * Allow `input_info` to be of type `None` * Handle errors (like OOM) more gracefully * Add a command-line argument to enable variants This allows the use of nodes that have sockets of type '*' without applying a patch to the code. * Fix an overly aggressive assertion. This could happen when attempting to evaluate `IS_CHANGED` for a node during the creation of the cache (in order to create the cache key). * Fix Pyright warnings * Add execution model unit tests * Fix issue with unused literals Behavior should now match the master branch with regard to undeclared inputs. Undeclared inputs that are socket connections will be used while undeclared inputs that are literals will be ignored. * Make custom VALIDATE_INPUTS skip normal validation Additionally, if `VALIDATE_INPUTS` takes an argument named `input_types`, that variable will be a dictionary of the socket type of all incoming connections. If that argument exists, normal socket type validation will not occur. This removes the last hurdle for enabling variant types entirely from custom nodes, so I've removed that command-line option. I've added appropriate unit tests for these changes. * Fix example in unit test This wouldn't have caused any issues in the unit test, but it would have bugged the UI if someone copy+pasted it into their own node pack. * Use fstrings instead of '%' formatting syntax * Use custom exception types. * Display an error for dependency cycles Previously, dependency cycles that were created during node expansion would cause the application to quit (due to an uncaught exception). Now, we'll throw a proper error to the UI. We also make an attempt to 'blame' the most relevant node in the UI. * Add docs on when ExecutionBlocker should be used * Remove unused functionality * Rename ExecutionResult.SLEEPING to PENDING * Remove superfluous function parameter * Pass None for uneval inputs instead of default This applies to `VALIDATE_INPUTS`, `check_lazy_status`, and lazy values in evaluation functions. * Add a test for mixed node expansion This test ensures that a node that returns a combination of expanded subgraphs and literal values functions correctly. * Raise exception for bad get_node calls. * Minor refactor of IsChangedCache.get * Refactor `map_node_over_list` function * Fix ui output for duplicated nodes * Add documentation on `check_lazy_status` * Add file for execution model unit tests * Clean up Javascript code as per review * Improve documentation Converted some comments to docstrings as per review * Add a new unit test for mixed lazy results This test validates that when an output list is fed to a lazy node, the node will properly evaluate previous nodes that are needed by any inputs to the lazy node. No code in the execution model has been changed. The test already passes. * Allow kwargs in VALIDATE_INPUTS functions When kwargs are used, validation is skipped for all inputs as if they had been mentioned explicitly. * List cached nodes in `execution_cached` message This was previously just bugged in this PR.
2024-08-15 08:21:11 -07:00
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.")
Execution Model Inversion (#2666) * Execution Model Inversion This PR inverts the execution model -- from recursively calling nodes to using a topological sort of the nodes. This change allows for modification of the node graph during execution. This allows for two major advantages: 1. The implementation of lazy evaluation in nodes. For example, if a "Mix Images" node has a mix factor of exactly 0.0, the second image input doesn't even need to be evaluated (and visa-versa if the mix factor is 1.0). 2. Dynamic expansion of nodes. This allows for the creation of dynamic "node groups". Specifically, custom nodes can return subgraphs that replace the original node in the graph. This is an incredibly powerful concept. Using this functionality, it was easy to implement: a. Components (a.k.a. node groups) b. Flow control (i.e. while loops) via tail recursion c. All-in-one nodes that replicate the WebUI functionality d. and more All of those were able to be implemented entirely via custom nodes, so those features are *not* a part of this PR. (There are some front-end changes that should occur before that functionality is made widely available, particularly around variant sockets.) The custom nodes associated with this PR can be found at: https://github.com/BadCafeCode/execution-inversion-demo-comfyui Note that some of them require that variant socket types ("*") be enabled. * Allow `input_info` to be of type `None` * Handle errors (like OOM) more gracefully * Add a command-line argument to enable variants This allows the use of nodes that have sockets of type '*' without applying a patch to the code. * Fix an overly aggressive assertion. This could happen when attempting to evaluate `IS_CHANGED` for a node during the creation of the cache (in order to create the cache key). * Fix Pyright warnings * Add execution model unit tests * Fix issue with unused literals Behavior should now match the master branch with regard to undeclared inputs. Undeclared inputs that are socket connections will be used while undeclared inputs that are literals will be ignored. * Make custom VALIDATE_INPUTS skip normal validation Additionally, if `VALIDATE_INPUTS` takes an argument named `input_types`, that variable will be a dictionary of the socket type of all incoming connections. If that argument exists, normal socket type validation will not occur. This removes the last hurdle for enabling variant types entirely from custom nodes, so I've removed that command-line option. I've added appropriate unit tests for these changes. * Fix example in unit test This wouldn't have caused any issues in the unit test, but it would have bugged the UI if someone copy+pasted it into their own node pack. * Use fstrings instead of '%' formatting syntax * Use custom exception types. * Display an error for dependency cycles Previously, dependency cycles that were created during node expansion would cause the application to quit (due to an uncaught exception). Now, we'll throw a proper error to the UI. We also make an attempt to 'blame' the most relevant node in the UI. * Add docs on when ExecutionBlocker should be used * Remove unused functionality * Rename ExecutionResult.SLEEPING to PENDING * Remove superfluous function parameter * Pass None for uneval inputs instead of default This applies to `VALIDATE_INPUTS`, `check_lazy_status`, and lazy values in evaluation functions. * Add a test for mixed node expansion This test ensures that a node that returns a combination of expanded subgraphs and literal values functions correctly. * Raise exception for bad get_node calls. * Minor refactor of IsChangedCache.get * Refactor `map_node_over_list` function * Fix ui output for duplicated nodes * Add documentation on `check_lazy_status` * Add file for execution model unit tests * Clean up Javascript code as per review * Improve documentation Converted some comments to docstrings as per review * Add a new unit test for mixed lazy results This test validates that when an output list is fed to a lazy node, the node will properly evaluate previous nodes that are needed by any inputs to the lazy node. No code in the execution model has been changed. The test already passes. * Allow kwargs in VALIDATE_INPUTS functions When kwargs are used, validation is skipped for all inputs as if they had been mentioned explicitly. * List cached nodes in `execution_cached` message This was previously just bugged in this PR.
2024-08-15 08:21:11 -07:00
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. Implies --enable-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.")
Threaded Loader performance fixes / improvements (+ Aimdo 0.4.6) (#14116) * memory_management: Add direct to read GPU mode Make destination optional (or make it optionally GPU) and use aimdo to file_read direct to GPU. * ops: Remove stream pin buffers and use aimdo reads This consumed too much RAM and its better to just take the hit on the CPU syncing back the stream on a short ring buffer. Aimdo implements this so just rip the stream pin buffer from comfy. * model_management: all active pin registration movement Its better to just let the active model load past the pin limit as pins and let the pins move around. The saves the HDD and SATA people disk traffic while only costing a few GPU syncs. * utils: use aimdo file handle This opens on windows with more favourable flags * mp: only count the model proper for loaded_ram and vram Exclude live loras from the numbers to avoid the case where the reported loaded memory exceeds the size of the model. This causes me confusion in the Kijai visualizer when it looked fully loaded but was hitting disk due to this accounding disrepency. * utils: add bit reverse utility useful for max scattering something ordered. * pinned_memory: Implement offload balancing Use a max scatter alogorithm to prioritize pins of the same size such that when doing a little bit of offloading it gets scattered, allowing the prefetcher to more evenly swollow the offload. * comfy-aimdo 0.4.7 Aimdo 0.4.7 implement VRAM buffer exhaustion predection to avoid early speculative load of weights that definately wont fix once the inference gets further in. * model-prefetch: consolidate pin ensures on the sync point This could happen mid prefetch block, cause a sync of the entire block and lose overlap. Get ahead of the problem with a free down at the natural compute stream sync point. * mm: Put a 2GB min on the pin ceiling This is reasonably bad if it starts causing swap pressure, moreso than during normal ram-cache proceedings. Clamp it. * add --fast-disk
2026-05-31 05:20:04 +10:00
parser.add_argument("--fast-disk", action="store_true", help="Prefer disk-backed dynamic loading and offload over unpinned RAM. Can be faster for users with fast NVME disks.")
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"
2025-09-02 02:33:50 +02:00
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("--debug-hang", action="store_true", help="Enable stack trace dumps on Ctrl-C for debugging hangs.")
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.")
More API Nodes (#7956) * Add Ideogram generate node. * Add staging api. * Add API_NODE and common error for missing auth token (#5) * Add Minimax Video Generation + Async Task queue polling example (#6) * [Minimax] Show video preview and embed workflow in ouput (#7) * Remove uv.lock * Remove polling operations. * Revert "Remove polling operations." * Update stubs. * Added Ideogram and Minimax back in. * Added initial BFL Flux 1.1 [pro] Ultra node (#11) * Add --comfy-api-base launch arg (#13) * Add instructions for staging development. (#14) * remove validation to make it easier to run against LAN copies of the API * Manually add BFL polling status response schema (#15) * Add function for uploading files. (#18) * Add Luma nodes (#16) * Refactor util functions (#20) * Add VIDEO type (#21) * Add rest of Luma node functionality (#19) * Fix image_luma_ref not working (#28) * [Bug] Remove duplicated option T2V-01 in MinimaxTextToVideoNode (#31) * Add utils to map from pydantic model fields to comfy node inputs (#30) * add veo2, bump av req (#32) * Add Recraft nodes (#29) * Add Kling Nodes (#12) * Add Camera Concepts (luma_concepts) to Luma Video nodes (#33) * Add Runway nodes (#17) * Convert Minimax node to use VIDEO output type (#34) * Standard `CATEGORY` system for api nodes (#35) * Set `Content-Type` header when uploading files (#36) * add better error propagation to veo2 (#37) * Add Realistic Image and Logo Raster styles for Recraft v3 (#38) * Fix runway image upload and progress polling (#39) * Fix image upload for Luma: only include `Content-Type` header field if it's set explicitly (#40) * Moved Luma nodes to nodes_luma.py (#47) * Moved Recraft nodes to nodes_recraft.py (#48) * Add Pixverse nodes (#46) * Move and fix BFL nodes to node_bfl.py (#49) * Move and edit Minimax node to nodes_minimax.py (#50) * Add Minimax Image to Video node + Cleanup (#51) * Add Recraft Text to Vector node, add Save SVG node to handle its output (#53) * Added pixverse_template support to Pixverse Text to Video node (#54) * Added Recraft Controls + Recraft Color RGB nodes (#57) * split remaining nodes out of nodes_api, make utility lib, refactor ideogram (#61) * Add types and doctstrings to utils file (#64) * Fix: `PollingOperation` progress bar update progress by absolute value (#65) * Use common download function in kling nodes module (#67) * Fix: Luma video nodes in `api nodes/image` category (#68) * Set request type explicitly (#66) * Add `control_after_generate` to all seed inputs (#69) * Fix bug: deleting `Content-Type` when property does not exist (#73) * Add preview to Save SVG node (#74) * change default poll interval (#76), rework veo2 * Add Pixverse and updated Kling types (#75) * Added Pixverse Image to VIdeo node (#77) * Add Pixverse Transition Video node (#79) * Proper ray-1-6 support as fix has been applied in backend (#80) * Added Recraft Style - Infinite Style Library node (#82) * add ideogram v3 (#83) * [Kling] Split Camera Control config to its own node (#81) * Add Pika i2v and t2v nodes (#52) * Temporary Fix for Runway (#87) * Added Stability Stable Image Ultra node (#86) * Remove Runway nodes (#88) * Fix: Prompt text can't be validated in Kling nodes when using primitive nodes (#90) * Fix: typo in node name "Stabiliy" => "Stability" (#91) * Add String (Multiline) node (#93) * Update Pika Duration and Resolution options (#94) * Change base branch to master. Not main. (#95) * Fix UploadRequest file_name param (#98) * Removed Infinite Style Library until later (#99) * fix ideogram style types (#100) * fix multi image return (#101) * add metadata saving to SVG (#102) * Bump templates version to include API node template workflows (#104) * Fix: `download_url_to_video_output` return type (#103) * fix 4o generation bug (#106) * Serve SVG files directly (#107) * Add a bunch of nodes, 3 ready to use, the rest waiting for endpoint support (#108) * Revert "Serve SVG files directly" (#111) * Expose 4 remaining Recraft nodes (#112) * [Kling] Add `Duration` and `Video ID` outputs (#105) * Fix: datamodel-codegen sets string#binary type to non-existent `bytes_aliased` variable (#114) * Fix: Dall-e 2 not setting request content-type dynamically (#113) * Default request timeout: one hour. (#116) * Add Kling nodes: camera control, start-end frame, lip-sync, video extend (#115) * Add 8 nodes - 4 BFL, 4 Stability (#117) * Fix error for Recraft ImageToImage error for nonexistent random_seed param (#118) * Add remaining Pika nodes (#119) * Make controls input work for Recraft Image to Image node (#120) * Use upstream PR: Support saving Comfy VIDEO type to buffer (#123) * Use Upstream PR: "Fix: Error creating video when sliced audio tensor chunks are non-c-contiguous" (#127) * Improve audio upload utils (#128) * Fix: Nested `AnyUrl` in request model cannot be serialized (Kling, Runway) (#129) * Show errors and API output URLs to the user (change log levels) (#131) * Fix: Luma I2I fails when weight is <=0.01 (#132) * Change category of `LumaConcepts` node from image to video (#133) * Fix: `image.shape` accessed before `image` is null-checked (#134) * Apply small fixes and most prompt validation (if needed to avoid API error) (#135) * Node name/category modifications (#140) * Add back Recraft Style - Infinite Style Library node (#141) * Fixed Kling: Check attributes of pydantic types. (#144) * Bump `comfyui-workflow-templates` version (#142) * [Kling] Print response data when error validating response (#146) * Fix: error validating Kling image response, trying to use `"key" in` on Pydantic class instance (#147) * [Kling] Fix: Correct/verify supported subset of input combos in Kling nodes (#149) * [Kling] Fix typo in node description (#150) * [Kling] Fix: CFG min/max not being enforced (#151) * Rebase launch-rebase (private) on prep-branch (public copy of master) (#153) * Bump templates version (#154) * Fix: Kling image gen nodes don't return entire batch when `n` > 1 (#152) * Remove pixverse_template from PixVerse Transition Video node (#155) * Invert image_weight value on Luma Image to Image node (#156) * Invert and resize mask for Ideogram V3 node to match masking conventions (#158) * [Kling] Fix: image generation nodes not returning Tuple (#159) * [Bug] [Kling] Fix Kling camera control (#161) * Kling Image Gen v2 + improve node descriptions for Flux/OpenAI (#160) * [Kling] Don't return video_id from dual effect video (#162) * Bump frontend to 1.18.8 (#163) * Use 3.9 compat syntax (#164) * Use Python 3.10 * add example env var * Update templates to 0.1.11 * Bump frontend to 1.18.9 --------- Co-authored-by: Robin Huang <robin.j.huang@gmail.com> Co-authored-by: Christian Byrne <cbyrne@comfy.org> Co-authored-by: thot experiment <94414189+thot-experiment@users.noreply.github.com>
2025-05-06 03:23:00 -05:00
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([])
2023-05-06 16:59:40 -04:00
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.
2026-05-21 10:03:58 +10:00
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")
2023-05-06 16:59:40 -04:00
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
# '--enable-manager-legacy-ui' is meaningless unless the manager is enabled, so imply '--enable-manager'.
if args.enable_manager_legacy_ui:
args.enable_manager = 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