Engine Validator:
PyTorch: 2.3.1+cu118 C(11080)____
OnnxRuntime: CUDA(11080)
------------------------
Port Info:
Exclusion List:
Non-administered:
5357..1
Administered:
In Use (v4):
135 => 1188
139 => 4
445 => 4
5037 => 14356
5040 => 6696
5283 => 2064
5354 => 4760
5357 => 4
7680 => 3380
10000 => 9516
10078 => 11556
10808 => 17444
10810 => 14912
14013 => 22848
14016 => 22848
14019 => 22848
14022 => 22848
14023 => 22848
22331 => 3312
22885 => 2180
27036 => 4392
27060 => 4392
33609 => 11216
49188 => 4392
49250 => 4908
49664 => 1012
49665 => 924
49666 => 1512
49667 => 1568
49668 => 3724
49669 => 4444
49671 => 1004
49853 => 12628
54022 => 3312
54360 => 11556
54421 => 11556
60048 => 4392
In Use (v6):
135 => 1188
445 => 4
5357 => 4
7680 => 3380
22331 => 3312
49664 => 1012
49665 => 924
49666 => 1512
49667 => 1568
49668 => 3724
49669 => 4444
49670 => 4948
49671 => 1004
54022 => 3312
------------------------
Config:
Audience Type: 新手
Lock Engine: True
Engine: CUDA GPU 0: NVIDIA GeForce GTX 1080 Ti (11 GB) [0]
VRAM Optimization: Auto [Auto]
Port: 8188 [8188]
XAttn Optimization: Xformers [Xformers]
CPU VAE: False [False]
Upcast Attention: True [True]
Precision: Auto [Auto]
Text Encoder Precision: Auto [Auto]
UNet Precision: Auto [Auto]
VAE Precision: Auto [Auto]
Force Channels Last: False [False]
Preview Method: Auto [Auto]
Smart Memory: True [True]
Deterministic: False [False]
Multi User: False [False]
Fast: False [False]
Listen: False [False]
Server Name: []
HF Offline Mode: False [False]
Cuda Allocator Backend: Native [Native]
Prevent Sysmem Fallback: False
Extra Args:
------------------------
Network Preferences:
Proxy Address:
http://127.0.0.1:10810Proxy Git: False
Proxy Pip: False
Proxy Model Download: False
Proxy Env: False
Mirror Pypi: True
Mirror Git: True
Mirror ExtensionList: True
Mirror Huggingface: True
Github Acceleration: False
------------------------
Log:
AttributeError: module 'torch.library' has no attribute 'custom_op'
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-02-02 06:09:54.270
** Platform: Windows
** Python version:
3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]
** Python executable: C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\python\python.exe
** ComfyUI Path: C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI
** ComfyUI Base Folder Path:
C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI
** User directory: C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\user
** ComfyUI-Manager config path: C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\user\__manager\config.ini
** Log path:
C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\user\comfyui.log
Prestartup times for custom nodes:
0.0 seconds: C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\custom_nodes\rgthree-comfy
9.4 seconds: C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\custom_nodes\ComfyUI-Manager
Warning, you are using an old pytorch version and some ckpt/pt files might be loaded unsafely. Upgrading to 2.4 or above is recommended as older versions of pytorch are no longer supported.
A module that was compiled using NumPy 1.x cannot be run in
NumPy 2.4.2 as it may crash. To support both 1.x and 2.x
versions of NumPy, modules must be compiled with NumPy 2.0.
Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.
If you are a user of the module, the easiest solution will be to
downgrade to 'numpy<2' or try to upgrade the affected module.
We expect that some modules will need time to support NumPy 2.
Traceback (most recent call last): File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\main.py", line 179, in <module>
import execution
File "<enhanced_experience utils.hook>", line 352, in exec_module
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\execution.py", line 16, in <module>
import comfy.memory_management
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\comfy\memory_management.py", line 5, in <module>
from comfy.quant_ops import QuantizedTensor
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\comfy\quant_ops.py", line 5, in <module>
import comfy_kitchen as ck
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\python\Lib\site-packages\comfy_kitchen\__init__.py", line 3, in <module>
from .backends import cuda as _cuda_backend # noqa: F401
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\python\Lib\site-packages\comfy_kitchen\backends\cuda\__init__.py", line 101, in <module>
from comfy_kitchen.backends.eager.quantization import DTYPE_TO_CODE # noqa: E402
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\python\Lib\site-packages\comfy_kitchen\backends\eager\__init__.py", line 11, in <module>
from .quantization import (
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\python\Lib\site-packages\comfy_kitchen\backends\eager\quantization.py", line 107, in <module>
E2M1_LUT = torch.tensor([
C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\python\Lib\site-packages\comfy_kitchen\backends\eager\quantization.py:107: UserWarning: Failed to initialize NumPy: _ARRAY_API not found (Triggered internally at ..\torch\csrc\utils\tensor_numpy.cpp:84.)
E2M1_LUT = torch.tensor([
Traceback (most recent call last):
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\main.py", line 179, in <module>
import execution
File "<frozen importlib._bootstrap>", line 1360, in _find_and_load
File "<frozen importlib._bootstrap>", line 1331, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 935, in _load_unlocked
File "<enhanced_experience utils.hook>", line 352, in exec_module
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\execution.py", line 16, in <module>
import comfy.memory_management
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\comfy\memory_management.py", line 5, in <module>
from comfy.quant_ops import QuantizedTensor
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\ComfyUI\comfy\quant_ops.py", line 5, in <module>
import comfy_kitchen as ck
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\python\Lib\site-packages\comfy_kitchen\__init__.py", line 3, in <module>
from .backends import cuda as _cuda_backend # noqa: F401
^^^^^
^^^^^^
^^^^^^
^^^^^^
^^^^^^
^^^^^^
^^^^^^
^^
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\python\Lib\site-packages\comfy_kitchen\backends\cuda\__init__.py", line 101, in <module>
from comfy_kitchen.backends.eager.quantization import DTYPE_TO_CODE # noqa: E402
^
^^^^^^
^^^^^^
^^^^^^
^^^^^^
^^^^^^
^^^^^^
^^^^^^
^^^^^^
^^^^^^
^^^^^^
^^^^^^
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\python\Lib\site-packages\comfy_kitchen\backends\eager\__init__.py", line 11, in <module>
from .quantization import (
File "C:\秋叶comfyui整合包\ComfyUI-aki-v2\ComfyUI-aki-v2\python\Lib\site-packages\comfy_kitchen\backends\eager\quantization.py", line 201, in <module>
@torch.library.custom_op("comfy_kitchen::quantize_fp8", mutates_args=())
^^^^
^^^^^^
^^^^^^
^^^^^^
^
AttributeError: module 'torch.library' has no attribute 'custom_op'
[Exited, code 1 (0x00000001)]
------------------------
Fault Traceback:
Not Available