ComfyUI/main.py

266 lines
9.5 KiB
Python
Raw Normal View History

import comfy.options
comfy.options.enable_args_parsing()
import os
import importlib.util
import folder_paths
import time
from comfy.cli_args import args
from app.logger import setup_logger
setup_logger(log_level=args.verbose)
def execute_prestartup_script():
def execute_script(script_path):
module_name = os.path.splitext(script_path)[0]
try:
spec = importlib.util.spec_from_file_location(module_name, script_path)
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
return True
except Exception as e:
print(f"Failed to execute startup-script: {script_path} / {e}")
return False
if args.disable_all_custom_nodes:
return
node_paths = folder_paths.get_folder_paths("custom_nodes")
for custom_node_path in node_paths:
possible_modules = os.listdir(custom_node_path)
node_prestartup_times = []
for possible_module in possible_modules:
module_path = os.path.join(custom_node_path, possible_module)
if os.path.isfile(module_path) or module_path.endswith(".disabled") or module_path == "__pycache__":
continue
script_path = os.path.join(module_path, "prestartup_script.py")
if os.path.exists(script_path):
time_before = time.perf_counter()
success = execute_script(script_path)
node_prestartup_times.append((time.perf_counter() - time_before, module_path, success))
if len(node_prestartup_times) > 0:
print("\nPrestartup times for custom nodes:")
for n in sorted(node_prestartup_times):
if n[2]:
import_message = ""
else:
import_message = " (PRESTARTUP FAILED)"
print("{:6.1f} seconds{}:".format(n[0], import_message), n[1])
print()
execute_prestartup_script()
# Main code
2023-04-06 00:32:59 +00:00
import asyncio
import itertools
import shutil
2023-01-03 06:53:32 +00:00
import threading
import gc
2024-03-11 20:24:47 +00:00
import logging
2024-09-10 04:43:37 +00:00
import utils.extra_config
2023-01-03 06:53:32 +00:00
if os.name == "nt":
logging.getLogger("xformers").addFilter(lambda record: 'A matching Triton is not available' not in record.getMessage())
2023-02-08 03:12:56 +00:00
if __name__ == "__main__":
2023-04-06 00:32:59 +00:00
if args.cuda_device is not None:
os.environ['CUDA_VISIBLE_DEVICES'] = str(args.cuda_device)
os.environ['HIP_VISIBLE_DEVICES'] = str(args.cuda_device)
2024-03-11 20:24:47 +00:00
logging.info("Set cuda device to: {}".format(args.cuda_device))
2023-04-06 00:32:59 +00:00
if args.deterministic:
if 'CUBLAS_WORKSPACE_CONFIG' not in os.environ:
os.environ['CUBLAS_WORKSPACE_CONFIG'] = ":4096:8"
import cuda_malloc
2023-04-06 00:32:59 +00:00
if args.windows_standalone_build:
try:
import fix_torch
except:
pass
import comfy.utils
import execution
2023-04-06 00:32:59 +00:00
import server
2023-05-31 01:43:29 +00:00
from server import BinaryEventTypes
import nodes
import comfy.model_management
def cuda_malloc_warning():
device = comfy.model_management.get_torch_device()
device_name = comfy.model_management.get_torch_device_name(device)
cuda_malloc_warning = False
if "cudaMallocAsync" in device_name:
for b in cuda_malloc.blacklist:
if b in device_name:
cuda_malloc_warning = True
if cuda_malloc_warning:
2024-03-11 20:24:47 +00:00
logging.warning("\nWARNING: this card most likely does not support cuda-malloc, if you get \"CUDA error\" please run ComfyUI with: --disable-cuda-malloc\n")
def prompt_worker(q, server):
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 15:21:11 +00:00
e = execution.PromptExecutor(server, lru_size=args.cache_lru)
last_gc_collect = 0
need_gc = False
gc_collect_interval = 10.0
2023-01-03 06:53:32 +00:00
while True:
timeout = 1000.0
if need_gc:
timeout = max(gc_collect_interval - (current_time - last_gc_collect), 0.0)
queue_item = q.get(timeout=timeout)
if queue_item is not None:
item, item_id = queue_item
execution_start_time = time.perf_counter()
prompt_id = item[1]
server.last_prompt_id = prompt_id
e.execute(item[2], prompt_id, item[3], item[4])
need_gc = True
2024-01-11 13:38:18 +00:00
q.task_done(item_id,
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 15:21:11 +00:00
e.history_result,
2024-01-11 13:38:18 +00:00
status=execution.PromptQueue.ExecutionStatus(
status_str='success' if e.success else 'error',
completed=e.success,
messages=e.status_messages))
if server.client_id is not None:
server.send_sync("executing", { "node": None, "prompt_id": prompt_id }, server.client_id)
current_time = time.perf_counter()
execution_time = current_time - execution_start_time
2024-03-11 20:24:47 +00:00
logging.info("Prompt executed in {:.2f} seconds".format(execution_time))
flags = q.get_flags()
free_memory = flags.get("free_memory", False)
if flags.get("unload_models", free_memory):
comfy.model_management.unload_all_models()
need_gc = True
last_gc_collect = 0
if free_memory:
e.reset()
need_gc = True
last_gc_collect = 0
if need_gc:
current_time = time.perf_counter()
if (current_time - last_gc_collect) > gc_collect_interval:
gc.collect()
comfy.model_management.soft_empty_cache()
last_gc_collect = current_time
need_gc = False
2023-06-07 13:15:38 +00:00
async def run(server, address='', port=8188, verbose=True, call_on_start=None):
addresses = []
for addr in address.split(","):
addresses.append((addr, port))
await asyncio.gather(server.start_multi_address(addresses, call_on_start), server.publish_loop())
2023-01-03 06:53:32 +00:00
2023-06-07 13:15:38 +00:00
def hijack_progress(server):
def hook(value, total, preview_image):
comfy.model_management.throw_exception_if_processing_interrupted()
progress = {"value": value, "max": total, "prompt_id": server.last_prompt_id, "node": server.last_node_id}
server.send_sync("progress", progress, server.client_id)
if preview_image is not None:
server.send_sync(BinaryEventTypes.UNENCODED_PREVIEW_IMAGE, preview_image, server.client_id)
comfy.utils.set_progress_bar_global_hook(hook)
2023-01-03 06:53:32 +00:00
2023-06-07 13:15:38 +00:00
def cleanup_temp():
temp_dir = folder_paths.get_temp_directory()
if os.path.exists(temp_dir):
shutil.rmtree(temp_dir, ignore_errors=True)
2023-06-07 13:15:38 +00:00
2023-01-03 06:53:32 +00:00
if __name__ == "__main__":
if args.temp_directory:
temp_dir = os.path.join(os.path.abspath(args.temp_directory), "temp")
2024-03-11 20:24:47 +00:00
logging.info(f"Setting temp directory to: {temp_dir}")
folder_paths.set_temp_directory(temp_dir)
cleanup_temp()
if args.windows_standalone_build:
try:
import new_updater
new_updater.update_windows_updater()
except:
pass
loop = asyncio.new_event_loop()
asyncio.set_event_loop(loop)
server = server.PromptServer(loop)
q = execution.PromptQueue(server)
extra_model_paths_config_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "extra_model_paths.yaml")
if os.path.isfile(extra_model_paths_config_path):
2024-09-10 04:43:37 +00:00
utils.extra_config.load_extra_path_config(extra_model_paths_config_path)
if args.extra_model_paths_config:
for config_path in itertools.chain(*args.extra_model_paths_config):
2024-09-10 04:43:37 +00:00
utils.extra_config.load_extra_path_config(config_path)
nodes.init_extra_nodes(init_custom_nodes=not args.disable_all_custom_nodes)
cuda_malloc_warning()
server.add_routes()
hijack_progress(server)
2023-06-07 13:15:38 +00:00
threading.Thread(target=prompt_worker, daemon=True, args=(q, server,)).start()
2023-02-08 02:57:17 +00:00
2023-04-06 00:32:59 +00:00
if args.output_directory:
output_dir = os.path.abspath(args.output_directory)
2024-03-11 20:24:47 +00:00
logging.info(f"Setting output directory to: {output_dir}")
folder_paths.set_output_directory(output_dir)
#These are the default folders that checkpoints, clip and vae models will be saved to when using CheckpointSave, etc.. nodes
folder_paths.add_model_folder_path("checkpoints", os.path.join(folder_paths.get_output_directory(), "checkpoints"))
folder_paths.add_model_folder_path("clip", os.path.join(folder_paths.get_output_directory(), "clip"))
folder_paths.add_model_folder_path("vae", os.path.join(folder_paths.get_output_directory(), "vae"))
2024-08-18 01:28:36 +00:00
folder_paths.add_model_folder_path("diffusion_models", os.path.join(folder_paths.get_output_directory(), "diffusion_models"))
folder_paths.add_model_folder_path("loras", os.path.join(folder_paths.get_output_directory(), "loras"))
2023-10-04 22:45:15 +00:00
if args.input_directory:
input_dir = os.path.abspath(args.input_directory)
2024-03-11 20:24:47 +00:00
logging.info(f"Setting input directory to: {input_dir}")
2023-10-04 22:45:15 +00:00
folder_paths.set_input_directory(input_dir)
if args.user_directory:
user_dir = os.path.abspath(args.user_directory)
logging.info(f"Setting user directory to: {user_dir}")
folder_paths.set_user_directory(user_dir)
2023-10-04 22:45:15 +00:00
2023-04-06 00:32:59 +00:00
if args.quick_test_for_ci:
exit(0)
os.makedirs(folder_paths.get_temp_directory(), exist_ok=True)
call_on_start = None
2023-05-06 20:59:40 +00:00
if args.auto_launch:
def startup_server(scheme, address, port):
import webbrowser
2023-08-01 05:14:17 +00:00
if os.name == 'nt' and address == '0.0.0.0':
address = '127.0.0.1'
if ':' in address:
address = "[{}]".format(address)
webbrowser.open(f"{scheme}://{address}:{port}")
call_on_start = startup_server
2023-06-07 13:15:38 +00:00
try:
loop.run_until_complete(server.setup())
2023-05-06 20:59:40 +00:00
loop.run_until_complete(run(server, address=args.listen, port=args.port, verbose=not args.dont_print_server, call_on_start=call_on_start))
2023-06-07 13:15:38 +00:00
except KeyboardInterrupt:
2024-03-11 20:24:47 +00:00
logging.info("\nStopped server")
2023-01-03 06:53:32 +00:00
cleanup_temp()