Merge branch 'master' into colored-logs

Use the RAM right up to the wire as the community is bit accustomed too.

This trades off headroom for the case where large chunky intermediates
arrive and potenitally hits pagefile/swap, but a lot of people have
"it just fits" workflows out there, so strike a compromise with
75->90%.

Disable the incative cache for all but the very high RAM users.

README.md

@@ -433,7 +433,7 @@ See also: [https://www.comfy.org/](https://www.comfy.org/)
 
 ## Frontend Development
 
-As of August 15, 2024, we have transitioned to a new frontend, which is now hosted in a separate repository: [ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend). This repository now hosts the compiled JS (from TS/Vue) under the `web/` directory.
+As of August 15, 2024, we have transitioned to a new frontend, which is now hosted in a separate repository: [ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend). The compiled JS files (from TS/Vue) are published to [pypi](https://pypi.org/project/comfyui-frontend-package) and installed as a dependency in ComfyUI.
 
 ### Reporting Issues and Requesting Features
 

app/logger.py

@@ -5,6 +5,40 @@ import logging
 import sys
 import threading
 
+ANSI_NAMED_COLORS = {
+    'black':   '\033[30m',
+    'red':     '\033[31m',
+    'green':   '\033[32m',
+    'yellow':  '\033[33m',
+    'blue':    '\033[34m',
+    'magenta': '\033[35m',
+    'cyan':    '\033[36m',
+    'white':   '\033[37m',
+}
+
+ANSI_LEVEL_COLORS = {
+    'DEBUG':    ANSI_NAMED_COLORS['cyan'],
+    'INFO':     ANSI_NAMED_COLORS['green'],
+    'WARNING':  ANSI_NAMED_COLORS['yellow'],
+    'ERROR':    ANSI_NAMED_COLORS['red'],
+    'CRITICAL': ANSI_NAMED_COLORS['magenta'],
+}
+
+ANSI_RESET = '\033[0m'
+ANSI_BOLD  = '\033[1m'
+
+
+class ColoredFormatter(logging.Formatter):
+    def format(self, record):
+        color = ANSI_LEVEL_COLORS.get(record.levelname, '')
+        bold  = ANSI_BOLD if record.levelno >= logging.WARNING else ''
+        level_tag = f"{bold}{color}[{record.levelname}]{ANSI_RESET} "
+        message = super().format(record)
+        line_color = ANSI_NAMED_COLORS.get(getattr(record, 'color', ''), '')
+        if line_color:
+            return f"{level_tag}{line_color}{message}{ANSI_RESET}"
+        return level_tag + message
+
 logs = None
 stdout_interceptor = None
 stderr_interceptor = None
@@ -68,8 +102,10 @@ def setup_logger(log_level: str = 'INFO', capacity: int = 300, use_stdout: bool
     logger = logging.getLogger()
     logger.setLevel(log_level)
 
+    formatter = ColoredFormatter("%(message)s")
+
     stream_handler = logging.StreamHandler()
-    stream_handler.setFormatter(logging.Formatter("%(message)s"))
+    stream_handler.setFormatter(formatter)
 
     if use_stdout:
         # Only errors and critical to stderr
@@ -77,7 +113,7 @@ def setup_logger(log_level: str = 'INFO', capacity: int = 300, use_stdout: bool
 
         # Lesser to stdout
         stdout_handler = logging.StreamHandler(sys.stdout)
-        stdout_handler.setFormatter(logging.Formatter("%(message)s"))
+        stdout_handler.setFormatter(formatter)
         stdout_handler.addFilter(lambda record: record.levelno < logging.ERROR)
         logger.addHandler(stdout_handler)
 

comfy/cli_args.py

@@ -111,7 +111,7 @@ parser.add_argument("--preview-method", type=LatentPreviewMethod, default=Latent
 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-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).")
 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.")

comfy/ldm/modules/attention.py

@@ -741,12 +741,12 @@ optimized_attention = attention_basic
 if model_management.sage_attention_enabled():
     logging.info("Using sage attention")
     optimized_attention = attention_sage
-elif model_management.xformers_enabled():
-    logging.info("Using xformers attention")
-    optimized_attention = attention_xformers
 elif model_management.flash_attention_enabled():
     logging.info("Using Flash Attention")
     optimized_attention = attention_flash
+elif model_management.xformers_enabled():
+    logging.info("Using xformers attention")
+    optimized_attention = attention_xformers
 elif model_management.pytorch_attention_enabled():
     logging.info("Using pytorch attention")
     optimized_attention = attention_pytorch

comfy/model_management.py

@@ -1217,7 +1217,7 @@ def get_aimdo_cast_buffer(offload_stream, device):
 def get_pin_buffer(offload_stream):
     pin_buffer = STREAM_PIN_BUFFERS.get(offload_stream, None)
     if pin_buffer is None:
-        pin_buffer = comfy_aimdo.host_buffer.HostBuffer(0, 0, pinned_hostbuf_size(8 * 1024**3))
+        pin_buffer = comfy_aimdo.host_buffer.HostBuffer(0, 0, pinned_hostbuf_size(8 * 1024**3), mark_cold=False)
         STREAM_PIN_BUFFERS[offload_stream] = pin_buffer
     elif offload_stream is not None:
         event = getattr(pin_buffer, "_comfy_event", None)

comfy/samplers.py

@@ -265,7 +265,6 @@ def _calc_cond_batch(model: BaseModel, conds: list[list[dict]], x_in: torch.Tens
                 input_shape = [len(batch_amount) * first_shape[0]] + list(first_shape)[1:]
                 cond_shapes = collections.defaultdict(list)
                 for tt in batch_amount:
-                    cond = {k: v.size() for k, v in to_run[tt][0].conditioning.items()}
                     for k, v in to_run[tt][0].conditioning.items():
                         cond_shapes[k].append(v.size())
 

main.py

@@ -286,8 +286,8 @@ def prompt_worker(q, server_instance):
     cache_ram = 0
     cache_ram_inactive = 0
     if not args.cache_classic and not args.cache_none and args.cache_lru <= 0:
-        cache_ram = min(32.0, max(4.0, comfy.model_management.total_ram * 0.25 / 1024.0))
-        cache_ram_inactive = min(96.0, max(12.0, comfy.model_management.total_ram * 0.75 / 1024.0))
+        cache_ram = min(10.0, max(2.0, comfy.model_management.total_ram * 0.10 / 1024.0))
+        cache_ram_inactive = min(96.0, comfy.model_management.total_ram / 1024.0)
         if len(args.cache_ram) > 0:
             cache_ram = args.cache_ram[0]
         if len(args.cache_ram) > 1:
@@ -344,9 +344,9 @@ def prompt_worker(q, server_instance):
             # Log Time in a more readable way after 10 minutes
             if execution_time > 600:
                 execution_time = time.strftime("%H:%M:%S", time.gmtime(execution_time))
-                logging.info(f"Prompt executed in {execution_time}")
+                logging.info(f"Prompt executed in {execution_time}", extra={'color': 'green'})
             else:
-                logging.info("Prompt executed in {:.2f} seconds".format(execution_time))
+                logging.info("Prompt executed in {:.2f} seconds".format(execution_time), extra={'color': 'green'})
 
             if not asset_seeder.is_disabled():
                 paths = _collect_output_absolute_paths(e.history_result)

openapi.yaml

@@ -9585,16 +9585,9 @@ components:
           description: List of plan features
 
     BillingStatus:
-      type: object
+      type: string
       x-runtime: [cloud]
-      description: "[cloud-only] Overall billing and subscription status."
-      properties:
-        subscription:
-          $ref: "#/components/schemas/BillingSubscription"
-        balance:
-          $ref: "#/components/schemas/BillingBalance"
-        has_payment_method:
-          type: boolean
+      description: "[cloud-only] Overall billing/payment lifecycle status."
       enum:
         - awaiting_payment_method
         - pending_payment

requirements.txt

@@ -1,4 +1,4 @@
-comfyui-frontend-package==1.43.18
+comfyui-frontend-package==1.44.19
 comfyui-workflow-templates==0.9.82
 comfyui-embedded-docs==0.5.0
 torch
@@ -23,7 +23,7 @@ SQLAlchemy>=2.0.0
 filelock
 av>=14.2.0
 comfy-kitchen>=0.2.8
-comfy-aimdo==0.4.3
+comfy-aimdo==0.4.5
 requests
 simpleeval>=1.0.0
 blake3