AttributeError: 'NoneType' object has no attribute 'dtype'我不懂为什么以前能用nunchaku出图，现在更新了comfyui后，反而用不了

Open

#13,102 opened on Mar 22, 2026 5 comments 1 reaction 0 assignees View on GitHub

Potential Bug

Dominant language: Python
Stars: 133k
Forks: 15.7k
Avg merge: 1d 7h
Merged PRs (30d): 158

Description

### Custom Node Testing

- [ ] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

AttributeError: 'NoneType' object has no attribute 'dtype'

### Actual Behavior

AttributeError: 'NoneType' object has no attribute 'dtype'
AttributeError: 'NoneType' object has no attribute 'dtype'

File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\execution.py", line 525, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\execution.py", line 334, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\execution.py", line 308, in _async_map_node_over_list
await process_inputs(input_dict, i)

File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\execution.py", line 296, in process_inputs
result = f(**inputs)
^^^^^^^^^^^

File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\nodes\models\zimage.py", line 215, in load_model
model = _load(sd, metadata=metadata)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\nodes\models\zimage.py", line 148, in _load
model = model_config.get_model(patched_sd, "", torch_dtype=torch_dtype)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\model_configs\zimage.py", line 71, in get_model
patch_model(

File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\models\zimage.py", line 320, in patch_model
_patch_transformer_block(diffusion_model.layers)

File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\models\zimage.py", line 317, in _patch_transformer_block
block.attention = ComfyNunchakuZImageAttention(block.attention, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\models\zimage.py", line 133, in __init__
self.qkv = SVDQW4A4Linear.from_linear(orig_attn.qkv, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\AI\ComfyUI-WorkFisher-V2\python\Lib\site-packages\nunchaku\models\linear.py", line 152, in from_linear
torch_dtype = kwargs.pop("torch_dtype", linear.weight.dtype)
^^^^^^^^^^^^^^^^^^^

### Steps to Reproduce

[nunchaku-z-image-turbo.json](https://github.com/user-attachments/files/26162742/nunchaku-z-image-turbo.json)

### Debug Logs

```powershell
ComfyUI Launcher Diagnostic File

Date: 2026-03-22 08:58:37
Launcher Version: 2.8.14.415
Data File Version: 2026-01-28 12:20
ComfyUI Version: dc719cde9c448c65242ae2d4ba400ba18c36846f (2026-03-21 08:09:15)
Working Directory: D:\AI\ComfyUI-WorkFisher-V2
App Directory: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI
------------------------
System Information:
OS: Microsoft Windows NT 10.0.19045.0
CPU: 12 cores
Memory Size: 0 MB Total, 10785 MB Free
Allocated Page File Size: 15360 MB Total, 14146 MB Free
Page File Settings: 0 MB Initial, 0 MB Maximum

NVIDIA Management Library:
NVIDIA Driver Version: 591.74
NVIDIA Management Library Version: 13.591.74

CUDA Driver:
Version: 13010
Devices:
00000000:01:00.0 0: NVIDIA GeForce RTX 4060 Ti [89] 15 GB

NvApi:
Version: 59174 r591_66

HIP Driver:
Not Available

DirectML Driver:
Devices:
10243 0: NVIDIA GeForce RTX 4060 Ti 15 GB

Intel Level Zero Driver:
Not Available

------------------------
Environment Variables:
IDEA_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\idea.vmoptions
PATHEXT=.COM;.EXE;.BAT;.CMD;.VBS;.VBE;.JS;.JSE;.WSF;.WSH;.MSC
CUDA_HOME=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8
PyCharm=E:\software\PyCharm 2024.1\bin;
conda=C:\Users\Administrator\anaconda3\_conda.exe
USERPROFILE=C:\Users\Administrator
RUBYMINE_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\rubymine.vmoptions
GATEWAY_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\gateway.vmoptions
WEBIDE_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\webide.vmoptions
STUDIO_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\studio.vmoptions
PYCHARM_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\pycharm.vmoptions
OS=Windows_NT
CLION_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\clion.vmoptions
XiuMaster_v1_button_hotkey=16777216
ProgramW6432=C:\Program Files
__COMPAT_LAYER=RunAsAdmin Installer
BESIEGE_GAME_ASSEMBLIES=E:/game/Besiege The Splintered Sea/Besiege_Data\Managed/
windir=C:\Windows
Python312=C:\Users\Administrator\AppData\Local\Programs\Python\Python312
wybxc/DocLayout-YOLO-DocStructBench-onnx=set HF_ENDPOINT=https://hf-mirror.com
OLLAMA_NUM_PARALLEL=1
ComSpec=C:\Windows\system32\cmd.exe
OLLAMA_KV_CACHE_TYPE=f16
ProgramFiles=C:\Program Files
Python312_s=C:\Users\Administrator\AppData\Local\Programs\Python\Python312\Scripts
HOMEDRIVE=C:
PROCESSOR_LEVEL=25
USERDOMAIN=DESKTOP-P1DLP6N
CommonProgramFiles=C:\Program Files\Common Files
ProgramData=C:\ProgramData
BESIEGE_UNITY_ASSEMBLIES=E:/game/Besiege The Splintered Sea/Besiege_Data\Managed/
SystemDrive=C:
USERDOMAIN_ROAMINGPROFILE=DESKTOP-P1DLP6N
CUDA_PATH_V12_8=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8
XiuMaster_v1_run_lua_2195=writeFloat("[[[[[ram10151431]+160]+20]+10]+20]+20","999");sendMessage(g_hwnd_ui,0x8004,g_xgq_id,"ok")
MOZ_PLUGIN_PATH=D:\ABOUTCG 教程播放器\
SystemRoot=C:\Windows
PROCESSOR_IDENTIFIER=AMD64 Family 25 Model 97 Stepping 2, AuthenticAMD
DATASPELL_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\dataspell.vmoptions
Path=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\bin;C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\libnvvp;C:\Program Files\Git\cmd;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0\;C:\Windows\System32\OpenSSH\;C:\Program Files\dotnet\;C:\Program Files (x86)\dotnet\;C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common;C:\ffmpeg\bin;C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\bin;C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8\libnvvp;C:\Program Files\nodejs\;C:\Program Files\CMake\bin;C:\Program Files (x86)\Windows Kits\10\Windows Performance Toolkit\;C:\Program Files\NVIDIA Corporation\Nsight Compute 2025.1.1\;C:\Program Files\NVIDIA Corporation\NVIDIA app\NvDLISR;C:\Program Files\Bandizip\;C:\Program Files\GitHub CLI\;C:\Users\Administrator\AppData\Roaming\npm;C:\Users\Administrator\.local\bin;C:\Users\Administrator\.copaw\bin;C:\Users\Administrator\AppData\Local\uv;C:\Users\Administrator\AppData\Local\Programs\Python\Python312;C:\Users\Administrator\.copaw\bin;C:\Users\Administrator\.local\bin;C:\Users\Administrator\AppData\Local\uv;C:\Users\Administrator\AppData\Local\Programs\Python\Python312\Scripts;C:\Users\Administrator\.copaw\bin;E:\AI\Qoder\bin;E:\AI\WorkBuddy\bin
CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8
DATAGRIP_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\datagrip.vmoptions
OLLAMA_ORIGINS=*
OneDrive=C:\Users\Administrator\OneDrive
PUBLIC=C:\Users\Public
OLLAMA_MODELS=E:\OllamaModels_save
JETBRAINS_CLIENT_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\jetbrains_client.vmoptions
TEMP=C:\Users\ADMINI~1\AppData\Local\Temp
GOLAND_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\goland.vmoptions
ALLUSERSPROFILE=C:\ProgramData
LOGONSERVER=\\DESKTOP-P1DLP6N
LOCALAPPDATA=C:\Users\Administrator\AppData\Local
PHPSTORM_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\phpstorm.vmoptions
DEVECOSTUDIO_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\devecostudio.vmoptions
OLLAMA_HOST=http://127.0.0.1:11434
APPDATA=C:\Users\Administrator\AppData\Roaming
NUMBER_OF_PROCESSORS=12
CC=d:\vs_Build_2022\VC\Tools\MSVC\14.44.35207\bin\Hostx64\x64\cl.exe
USERNAME=Administrator
TMP=C:\Users\ADMINI~1\AppData\Local\Temp
DriverData=C:\Windows\System32\Drivers\DriverData
APPCODE_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\appcode.vmoptions
JETBRAINSCLIENT_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\jetbrainsclient.vmoptions
HOMEPATH=\Users\Administrator
COMPUTERNAME=DESKTOP-P1DLP6N
PSModulePath=C:\Program Files\WindowsPowerShell\Modules;C:\Windows\system32\WindowsPowerShell\v1.0\Modules
RIDER_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\rider.vmoptions
ProgramFiles(x86)=C:\Program Files (x86)
PROCESSOR_REVISION=6102
PROCESSOR_ARCHITECTURE=AMD64
WEBSTORM_VM_OPTIONS=E:\桌面备份\Pycharm 2024.1\Crack\jetbra\vmoptions\webstorm.vmoptions
CommonProgramFiles(x86)=C:\Program Files (x86)\Common Files
CommonProgramW6432=C:\Program Files\Common Files
------------------------
Paths:
Python: D:\AI\ComfyUI-WorkFisher-V2\python\python.exe
- Python Paths:
- D:\AI\ComfyUI-WorkFisher-V2\python\DLLs
- D:\AI\ComfyUI-WorkFisher-V2\python\Lib
- D:\AI\ComfyUI-WorkFisher-V2\python
- D:\AI\ComfyUI-WorkFisher-V2\python\Lib\site-packages
- D:\AI\ComfyUI-WorkFisher-V2\python\Lib\site-packages\win32
- D:\AI\ComfyUI-WorkFisher-V2\python\Lib\site-packages\win32\lib
- D:\AI\ComfyUI-WorkFisher-V2\python\Lib\site-packages\Pythonwin
- Python Packages:
- absl_py 2.3.0
- accelerate 1.12.0
- addict 2.4.0
- aiofiles 24.1.0
- aiohappyeyeballs 2.6.1
- aiohttp 3.12.13
- aiohttp_cors 0.8.1
- aiohttp_socks 0.10.1
- aiosignal 1.3.2
- albucore 0.0.24
- albumentations 2.0.8
- alembic 1.16.2
- annotated_types 0.7.0
- antlr4_python3_runtime 4.9.3
- anyio 4.9.0
- argostranslate 1.9.6
- attrs 25.3.0
- av 14.4.0
- beautifulsoup4 4.13.4
- bitsandbytes 0.48.1
- blake3 1.0.8
- blend_modes 2.2.0
- blobfile 3.1.0
- boto3 1.34.86
- botocore 1.34.162
- brotli 1.2.0
- build 1.4.0
- cachetools 6.1.0
- certifi 2025.11.12
- cffi 2.0.0
- cfgv 3.4.0
- chardet 5.2.0
- charset_normalizer 3.4.4
- click 8.2.1
- clip_interrogator 0.6.0
- cmake 4.1.2
- colorama 0.4.6
- coloredlogs 15.0.1
- colorlog 6.9.0
- color_matcher 0.6.0
- colour_science 0.4.6
- comfyui_embedded_docs 0.4.3
- comfyui_frontend_package 1.41.21
- comfyui_workflow_templates 0.9.26
- comfyui_workflow_templates_core 0.3.173
- comfyui_workflow_templates_media_api 0.3.64
- comfyui_workflow_templates_media_image 0.3.107
- comfyui_workflow_templates_media_other 0.3.146
- comfyui_workflow_templates_media_video 0.3.62
- comfy_aimdo 0.2.12
- comfy_kitchen 0.2.8
- contourpy 1.3.2
- cryptography 46.0.3
- cssselect2 0.8.0
- cstr 0.1.0
- ctranslate2 4.6.0
- cupy_cuda12x 13.6.0
- cycler 0.12.1
- cython 3.1.2
- datasets 4.4.2
- ddgs 9.10.0
- ddt 1.7.2
- decord 0.6.0
- deepdiff 8.6.1
- deep_translator 1.11.4
- Deprecated 1.2.18
- diffusers 0.36.0
- dill 0.4.0
- diskcache 5.6.3
- distlib 0.4.0
- distro 1.9.0
- dlib 19.24.99
- docstring_parser 0.17.0
- docutils 0.21.2
- dotenv 0.9.9
- easydict 1.13
- einops 0.8.1
- einx 0.3.0
- et_xmlfile 2.0.0
- facexlib 0.3.0
- fairscale 0.4.13
- fake_useragent 2.2.0
- fal_client 0.8.1
- faster_whisper 1.2.0
- fastrlock 0.8.3
- ffmpy 0.3.0
- filelock 3.20.1
- filterpy 1.4.5
- flatbuffers 25.2.10
- fonttools 4.58.4
- frozendict 2.4.7
- frozenlist 1.7.0
- fsspec 2025.10.0
- ftfy 6.1.1
- future 1.0.0
- fvcore 0.1.5.post20221221
- gdown 5.2.0
- geographiclib 2.1
- geopy 2.4.1
- gguf 0.17.1
- gitdb 4.0.12
- GitPython 3.1.44
- glfw 2.10.0
- googletrans_py 4.0.0
- greenlet 3.2.3
- groundingdino_py 0.4.0
- h11 0.16.0
- h2 4.2.0
- hf_transfer 0.1.9
- hf_xet 1.2.0
- hpack 4.1.0
- httpcore 1.0.9
- httpx 0.28.1
- httpx_sse 0.4.3
- huggingface_hub 0.36.0
- humanfriendly 10.0
- hydra_core 1.3.2
- hyperframe 6.1.0
- identify 2.6.15
- idna 3.11
- imageio 2.37.0
- imageio_ffmpeg 0.6.0
- img2texture 1.0.6
- importlib_metadata 8.7.0
- iniconfig 2.3.0
- insightface 0.7.3
- instructor 1.11.3
- iopath 0.1.10
- jax 0.6.2
- jaxlib 0.6.2
- jinja2 3.1.6
- jiter 0.10.0
- jmespath 1.0.1
- joblib 1.5.1
- jsonschema 4.24.0
- jsonschema_specifications 2025.4.1
- json_repair 0.52.3
- kagglehub 0.4.1
- kagglesdk 0.1.15
- kaldi_native_fbank 1.22.3
- kiwisolver 1.4.8
- kornia 0.8.1
- kornia_rs 0.1.9
- lark 1.3.0
- lark_parser 0.12.0
- lazy_loader 0.4
- lightning_utilities 0.15.2
- llama_cpp_python 0.3.18
- llvmlite 0.45.1
- loguru 0.7.3
- loralib 0.1.2
- lxml 6.0.0
- mako 1.3.10
- manifold3d 3.1.1
- mapbox_earcut 1.0.3
- markdown_it_py 3.0.0
- markupsafe 3.0.3
- matplotlib 3.10.3
- matrix_client 0.4.0
- matrix_nio 0.25.2
- mdurl 0.1.2
- mediapipe 0.10.21
- ml_dtypes 0.5.1
- modelscope 1.33.0
- mpmath 1.3.0
- mss 10.0.0
- multidict 6.6.2
- multiprocess 0.70.18
- natsort 8.4.0
- nest_asyncio 1.6.0
- networkx 3.3
- ninja 1.11.1.4
- nodeenv 1.9.1
- ntplib 0.4.0
- numba 0.62.1
- numpy 1.26.4
- nunchaku 1.2.1+cu12.8torch2.8
- nvidia_ml_py 13.580.82
- ollama 0.6.0
- omegaconf 2.3.0
- onnx 1.18.0
- onnxruntime 1.22.0
- onnxruntime_gpu 1.22.0
- openai 1.109.1
- opencv_contrib_python 4.8.0.76
- opencv_contrib_python_headless 4.11.0.86
- opencv_python 4.8.0.76
- opencv_python_headless 4.9.0.80
- openpyxl 3.1.5
- open_clip_torch 3.2.0
- optimum 2.1.0
- opt_einsum 3.4.0
- orderly_set 5.5.0
- packaging 25.0
- pandas 2.3.3
- peft 0.17.0
- piexif 1.1.3
- pilgram 1.2.1
- pillow 12.0.0
- pip 25.3
- pipdeptree 2.30.0
- pixeloe 0.1.4
- platformdirs 4.3.8
- pluggy 1.6.0
- polars 1.34.0
- polars_runtime_32 1.34.0
- pooch 1.8.2
- portalocker 3.2.0
- prettytable 3.16.0
- pre_commit 4.3.0
- primp 0.15.0
- propcache 0.3.2
- protobuf 4.25.8
- psutil 7.0.0
- pyarrow 22.0.0
- pycocotools 2.0.10
- pycollada 0.9.1
- pycparser 2.22
- pycryptodome 3.23.0
- pycryptodomex 3.23.0
- pydantic 2.11.7
- pydantic_core 2.33.2
- pydantic_settings 2.10.1
- PyGithub 2.6.1
- pygments 2.19.2
- PyJWT 2.10.1
- pyloudnorm 0.1.1
- pymatting 1.1.14
- PyNaCl 1.5.0
- pynvml 13.0.1
- pyopengl 3.1.10
- pyopengl_accelerate 3.1.10
- pyopenssl 25.3.0
- pyparsing 3.2.3
- pyproject_hooks 1.2.0
- pyreadline3 3.5.4
- PySocks 1.7.1
- pytest 8.4.2
- python_dateutil 2.9.0.post0
- python_dotenv 1.1.1
- python_socks 2.7.1
- pytorch_extension 0.2
- pytorch_lightning 2.5.5
- pytz 2025.2
- pywavelets 1.9.0
- pywin32 310
- pyyaml 6.0.3
- py_cpuinfo 9.0.0
- qwen_vl_utils 0.0.14
- redis 7.1.0
- referencing 0.36.2
- regex 2025.11.3
- rembg 2.0.66
- replicate 1.0.7
- reportlab 4.4.2
- requests 2.32.5
- rich 14.0.0
- rotary_embedding_torch 0.8.9
- rpds_py 0.25.1
- rtree 1.4.0
- s3transfer 0.10.4
- sacremoses 0.0.53
- safetensors 0.7.0
- sageattention 2.2.0+cu128torch2.8.0
- sam_2 1.0
- scenedetect 0.6.7.1
- scikit_image 0.25.2
- scikit_learn 1.7.0
- scipy 1.16.0
- segment_anything 1.0
- sentencepiece 0.2.0
- setuptools 80.9.0
- shapely 2.1.1
- shellingham 1.5.4
- simpleeval 1.0.4
- simsimd 6.4.9
- six 1.17.0
- smmap 5.0.2
- sniffio 1.3.1
- socksio 1.0.0
- sounddevice 0.5.2
- soundfile 0.13.1
- soupsieve 2.7
- spandrel 0.4.1
- sqlalchemy 2.0.41
- stanza 1.1.1
- stringzilla 3.12.5
- supervision 0.6.0
- surrealist 1.1.2
- svg.path 6.3
- svglib 1.5.1
- swarm 0.1.0
- sympy 1.13.3
- tabulate 0.9.0
- tenacity 9.1.2
- termcolor 3.1.0
- threadpoolctl 3.6.0
- tifffile 2025.6.11
- tiktoken 0.12.0
- timm 1.0.19
- tinycss2 1.4.0
- tokenizers 0.22.2
- toml 0.10.2
- tomli 2.2.1
- torch 2.8.0+cu128
- torchao 0.15.0
- torchaudio 2.8.0+cu128
- torchcodec 0.10.0
- torchdata 0.11.0
- torchmetrics 1.8.2
- torchsde 0.2.6
- torchtune 0.6.1
- torchvision 0.23.0+cu128
- tqdm 4.67.1
- trampoline 0.1.2
- transformers 4.57.3
- transparent_background 1.3.4
- trimesh 4.6.13
- triton_windows 3.5.1.post23
- typer 0.16.0
- typing_extensions 4.15.0
- typing_inspection 0.4.1
- tzdata 2025.3
- ultralytics 8.3.221
- ultralytics_thop 2.0.17
- unpaddedbase64 2.1.0
- urllib3 1.26.20
- uv 0.7.17
- vector_quantize_pytorch 1.27.20
- vhacdx 0.0.8.post2
- virtualenv 20.35.3
- watchdog 6.0.0
- wcwidth 0.2.14
- webcolors 24.11.1
- webencodings 0.5.1
- websocket_client 1.9.0
- wget 3.2
- wheel 0.45.1
- win32_setctime 1.2.0
- wrapt 1.17.2
- xxhash 3.5.0
- yacs 0.1.8
- yapf 0.43.0
- yarl 1.20.1
- zipp 3.23.0
Git: D:\AI\ComfyUI-WorkFisher-V2\.ext\Library\cmd\git.exe
Shell: C:\Windows\system32\cmd.exe
Cache Path: D:\AI\ComfyUI-WorkFisher-V2\.cache
------------------------
Engine Validator:
PyTorch: 2.8.0+cu128 C(12080)____
OnnxRuntime: CUDA(12020)
------------------------
Port Info:
Exclusion List:
Non-administered:

Administered:
50000..60
In Use (v4):
80 => 10004
135 => 1248
139 => 4
443 => 10004
445 => 4
1001 => 4
1026 => 1000
4001 => 8440
4301 => 8440
4310 => 8440
5040 => 7076
5283 => 8440
8080 => 14188
8188 => 26512
9210 => 8440
10808 => 18284
10811 => 240
11046 => 13756
13322 => 17128
41593 => 25332
41595 => 15924
41596 => 27296
49664 => 336
49665 => 928
49666 => 1656
49667 => 1740
49668 => 4728
59177 => 11888
In Use (v6):
135 => 1248
445 => 4
1026 => 1000
8080 => 14188
10811 => 240
41593 => 25332
41595 => 15924
49664 => 336
49665 => 928
49666 => 1656
49667 => 1740
49668 => 4728
------------------------
Config:
Audience Type: 高级
Lock Engine: True
Engine: CUDA GPU 0: NVIDIA GeForce RTX 4060 Ti (16 GB) [0]
VRAM Optimization: Auto [Auto]
Port: 8188 [8188]
XAttn Optimization: Xformers [SageAttention]
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 [CudaMallocAsync]
Prevent Sysmem Fallback: True
Extra Args:
------------------------
Network Preferences:
Proxy Address: http://127.0.0.1:7897
Proxy 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: True
------------------------
Log:
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-03-22 08:54:52.055
** 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: D:\AI\ComfyUI-WorkFisher-V2\python\python.exe
** ComfyUI Path: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI
** ComfyUI Base Folder Path: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI
** User directory: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\user
** ComfyUI-Manager config path: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\user\__manager\config.ini
** Log path: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\user\comfyui.log

Prestartup times for custom nodes:
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\rgthree-comfy
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-easy-use
8.4 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-Manager

WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.
Found comfy_kitchen backend cuda: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4']}
Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
Checkpoint files will always be loaded safely.
Total VRAM 16380 MB, total RAM 32375 MB
pytorch version: 2.8.0+cu128
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4060 Ti : native
Using async weight offloading with 2 streams
Enabled pinned memory 14568.0
Using pytorch attention
aimdo: src-win/cuda-detour.c:77:INFO:aimdo_setup_hooks: found driver at 00007FFFF8690000, installing 4 hooks
aimdo: src-win/cuda-detour.c:61:DEBUG:install_hook_entrys: hooks successfully installed
aimdo: src/control.c:69:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 4060 Ti (VRAM: 16379 MB)
DynamicVRAM support detected and enabled
Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]
ComfyUI version: 0.18.0
comfy-aimdo version: 0.2.12
comfy-kitchen version: 0.2.8
ComfyUI frontend version: 1.41.21
[Prompt Server] web root: D:\AI\ComfyUI-WorkFisher-V2\python\Lib\site-packages\comfyui_frontend_package\static
Asset seeder disabled
Web extensions folder found at D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\web\extensions\ComfyLiterals
[Crystools [0;32mINFO[0m] Crystools version: 1.27.4
[Crystools [0;32mINFO[0m] Platform release: 10
[Crystools [0;32mINFO[0m] JETSON: Not detected.
[Crystools [0;32mINFO[0m] CPU: AMD Ryzen 5 7500F 6-Core Processor - Arch: AMD64 - OS: Windows 10
[Crystools [0;32mINFO[0m] pynvml (NVIDIA) initialized.
[Crystools [0;32mINFO[0m] GPU/s:
[Crystools [0;32mINFO[0m] 0) NVIDIA GeForce RTX 4060 Ti
[Crystools [0;32mINFO[0m] NVIDIA Driver: 591.74
Skipping import of cpp extensions due to incompatible torch version 2.8.0+cu128 for torchao version 0.15.0 Please see https://github.com/pytorch/ao/issues/2919 for more info
W0322 08:55:16.200000 26512 site-packages\torch\distributed\elastic\multiprocessing\redirects.py:29] NOTE: Redirects are currently not supported in Windows or MacOs.
Exception in thread
Thread-13 (_readerthread)
:
Traceback (most recent call last):
File "D:\AI\ComfyUI-WorkFisher-V2\python\Lib\threading.py", line 1075, in _bootstrap_inner

self.run()

File "", line 99, in run
File "", line 94, in _run_old_run_func
File "", line 1649, in reraise
File "", line 92, in _run_old_run_func
File "D:\AI\ComfyUI-WorkFisher-V2\python\Lib\threading.py", line 1012, in run

self._target(*self._args, **self._kwargs)

File "D:\AI\ComfyUI-WorkFisher-V2\python\Lib\subprocess.py", line 1599, in _readerthread

buffer.append(fh.read())

^
^
^
^
^
^
^
^
^

File "", line 322, in decode
UnicodeDecodeError
:
'utf-8' codec can't decode byte 0xb2 in position 7: invalid start byte

[ComfyUI-Easy-Use] server: v1.3.7
Loaded
[ComfyUI-Easy-Use] web root:
D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-easy-use\web_version/v2
Loaded

ComfyUI-GGUF: Allowing full torch compile
Unable to import guidedFilter, make sure you have only opencv-contrib-python or run the import_error_install.bat script
### Loading: ComfyUI-Impact-Pack (V8.28.2)
### Loading: ComfyUI-Impact-Subpack (V1.3.5)
[Impact Pack/Subpack] Using folder_paths to determine whitelist path: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
[Impact Pack/Subpack] Ensured whitelist directory exists: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\user\default\ComfyUI-Impact-Subpack
[Impact Pack/Subpack] Loaded 0 model(s) from whitelist: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
[Impact Subpack] ultralytics_bbox: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\models\ultralytics\bbox
[Impact Subpack] ultralytics_segm: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\models\ultralytics\segm
[Impact Pack] custom_wildcards path not found: F:\ComfyUI-aki-v2\ComfyUI\custom_nodes\comfyui-impact-pack\modules\impact\..\..\custom_wildcards. Using default path.
[Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
[Impact Pack] Wildcards loading done.
[LaoLi Lineup]
插件已加载：显存排队系统准备就绪

[llama-cpp_vlm] Model cleanup hook applied!

### Loading: ComfyUI-Manager (V3.39.2)
[ComfyUI-Manager] network_mode: public
[ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
### ComfyUI Version: v0.18.0 | Released on '2026-03-20'
======================================== ComfyUI-nunchaku Initialization ========================================
Nunchaku version: 1.2.1
ComfyUI-nunchaku version: 1.2.1
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
'nunchaku_versions.json' not found. Node will start in minimal mode. Use 'update node' to fetch versions.
=================================================================================================================
======================================== ComfyUI-QwenImageLoraLoader Initialization ========================================
[DEBUG] Added to sys.path: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-QwenImageLoraLoader

[DEBUG] wrappers dir exists: True

[DEBUG] qwenimage.py exists: True

✅ ControlNet node loaded successfully
============================================================================================================================
[ComfyUI-RMBG] v
3.0.0 |
43 nodes

Loaded

`flash-attention` package not found, consider installing for better performance: No module named 'flash_attn'.
Current `flash-attenton` does not support `window_size`. Either upgrade or use `attn_implementation='eager'`.
FlashAttention is not installed.

FlashAttention is not installed.

⚡ SeedVR2 optimizations check: SageAttention ✅ | Flash Attention ❌ | Triton ✅

💡 Optional: pip install flash-attn

📊 Initial CUDA memory: 14.83GB free / 16.00GB total
### ComfyUI-Workflow-Encrypt: Copy .js from 'D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-workflow-encrypt\js\comfyui-workflow-encrypt.js' to 'D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\web\extensions\comfyui-workflow-encrypt'

FETCH ComfyRegistry Data: 5/133
------------------------------------------

Comfyroll Studio v1.76 :
175 Nodes Loaded

------------------------------------------

** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md

** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki

------------------------------------------

[D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts

[D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False

[D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']

DWPose: Onnxruntime with acceleration providers detected

# 😺dzNodes: LayerStyle ->
Cannot import name 'guidedFilter' from 'cv2.ximgproc'
A few nodes cannot works properly, while most nodes are not affected. Please REINSTALL package 'opencv-contrib-python'.
For detail refer to
https://github.com/chflame163/ComfyUI_LayerStyle/issues/5

[32m ** Comfly Loaded :[33m Go Younjung Is My Favorite Girl!--T8star[0m
Traceback (most recent call last):
File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\nodes.py", line 2227, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 995, in exec_module
File "", line 1132, in get_code
File "", line 1190, in get_data
FileNotFoundError: [Errno 2] No such file or directory: 'D:\\AI\\ComfyUI-WorkFisher-V2\\ComfyUI\\custom_nodes\\DiffSynth-Studio\\__init__.py'

Cannot import D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\DiffSynth-Studio module for custom nodes: [Errno 2] No such file or directory: 'D:\\AI\\ComfyUI-WorkFisher-V2\\ComfyUI\\custom_nodes\\DiffSynth-Studio\\__init__.py'
✨提示词小助手 V2.0.4 已启动

Please 'pip install xformers'
Nvidia APEX normalization not installed, using PyTorch LayerNorm

Using pytorch attention
(RES4LYF) Init
(RES4LYF) Importing beta samplers.

(RES4LYF) Importing legacy samplers.

[rgthree-comfy] Loaded 48 exciting nodes. 🎉

[rgthree-comfy] ComfyUI's new Node 2.0 rendering may be incompatible with some rgthree-comfy nodes and features, breaking some rendering as well as losing the ability to access a node's properties (a vital part of many nodes). It also appears to run MUCH more slowly spiking CPU usage and causing jankiness and unresponsiveness, especially with large workflows. Personally I am not planning to use the new Nodes 2.0 and, unfortunately, am not able to invest the time to investigate and overhaul rgthree-comfy where needed. If you have issues when Nodes 2.0 is enabled, I'd urge you to switch it off as well and join me in hoping ComfyUI is not planning to deprecate the existing, stable canvas rendering all together.

WAS Node Suite: OpenCV Python FFMPEG support is enabled

WAS Node Suite
Warning:
`ffmpeg_bin_path` is not set in `D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\was-ns\was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.

WAS Node Suite: Finished.

Loaded

220

nodes successfully.

"Success is not final, failure is not fatal: It is the courage to continue that counts."
- Winston Churchill

Import times for custom nodes:
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\websocket_image_save.py
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui_memory_cleanup
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\Comfyui_Prompt_Edit
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-LaoLi-lineup
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\wanblockswap
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-PainterI2V
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-qwenmultiangle
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-qwenmultianglelight
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-WanMoeKSampler
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-mxToolkit
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-DD-Translation
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui_ttp_toolset
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-ReservedVRAM
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\HeartMuLa_ComfyUI
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\cg-use-everywhere
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-fbcnn
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\qweneditutils
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyLiterals
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-inpaint-cropandstitch
0.0 seconds (IMPORT FAILED): D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\DiffSynth-Studio
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ACE-Step-ComfyUI
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-Qwen-Image-Integrated-KSampler
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui_instantid
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-GGUF
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-impact-subpack
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-inpaint-nodes
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-Wan22FMLF
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\LanPaint
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-WanAnimatePreprocess
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-QwenImageLoraLoader
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-QwenVL
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-meancache-z
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-various
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui_essentials
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyMath
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI_Qwen3-VL-Instruct
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-custom-scripts
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\derfuu_comfyui_moddednodes
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-frame-interpolation
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-segment-anything-2
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-advanced-controlnet
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\prompt-assistant
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\rgthree-comfy
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-workflow-encrypt
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes
0.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\Comfyui-SecNodes
0.1 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui_controlnet_aux
0.1 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui_faceanalysis
0.1 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\pulid_comfyui
0.1 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-kjnodes
0.1 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-llama-cpp
0.1 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-Live-Search
0.2 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-tensorops
0.2 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui_layerstyle
0.2 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI_StringOps
0.3 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-SeedVR2_VideoUpscaler
0.3 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-florence2
0.3 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\RES4LYF
0.4 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-rmbg
0.4 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\Comfyui-zhenzhen
0.4 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-Crystools
0.4 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-ollama
0.5 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-impact-pack
0.5 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper
1.0 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-Manager
1.2 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-videohelpersuite
1.2 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-Image-Filters
1.3 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku
1.9 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-1hewNodes
3.7 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\was-ns
7.4 seconds: D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\comfyui-easy-use

Context impl SQLiteImpl.
Will assume non-transactional DDL.
Context impl SQLiteImpl.
Will assume non-transactional DDL.
Running upgrade 0002_merge_to_asset_references -> 0003_add_metadata_job_id, Add system_metadata and job_id columns to asset_references.
Change preview_id FK from assets.id to asset_references.id.
Database upgraded from 0002_merge_to_asset_references to 0003_add_metadata_job_id
Starting server

To see the GUI go to: http://127.0.0.1:8188
FETCH ComfyRegistry Data: 10/133
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/clipspace.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[修改] 已更新工作流路径：Flux2+Klein+超强多功能工作流.json
FETCH ComfyRegistry Data: 15/133
FETCH ComfyRegistry Data: 20/133
FETCH ComfyRegistry Data: 25/133
[修改] 已更新工作流路径：nunchaku-z-image-turbo.json
FETCH ComfyRegistry Data: 30/133
FETCH ComfyRegistry Data: 35/133
got prompt
Using pytorch attention in VAE
Using pytorch attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
Requested to load ZImageTEModel_
Model ZImageTEModel_ prepared for dynamic VRAM loading. 7671MB Staged. 0 patches attached. Force pre-loaded 145 weights: 383 KB.
FETCH ComfyRegistry Data: 40/133
FETCH ComfyRegistry Data: 45/133
FETCH ComfyRegistry Data: 50/133
unet_dtype: torch.bfloat16, manual_cast_dtype: None, svdq_linear_dtype: torch.bfloat16
model weight dtype torch.bfloat16, manual cast: None
model_type FLOW
!!! Exception during processing !!! 'NoneType' object has no attribute 'dtype'
Traceback (most recent call last):
File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\execution.py", line 525, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\execution.py", line 334, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\execution.py", line 308, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\execution.py", line 296, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\nodes\models\zimage.py", line 215, in load_model
model = _load(sd, metadata=metadata)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\nodes\models\zimage.py", line 148, in _load
model = model_config.get_model(patched_sd, "", torch_dtype=torch_dtype)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\model_configs\zimage.py", line 71, in get_model
patch_model(
File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\models\zimage.py", line 320, in patch_model
_patch_transformer_block(diffusion_model.layers)
File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\models\zimage.py", line 317, in _patch_transformer_block
block.attention = ComfyNunchakuZImageAttention(block.attention, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI-WorkFisher-V2\ComfyUI\custom_nodes\ComfyUI-nunchaku\models\zimage.py", line 133, in __init__
self.qkv = SVDQW4A4Linear.from_linear(orig_attn.qkv, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI-WorkFisher-V2\python\Lib\site-packages\nunchaku\models\linear.py", line 152, in from_linear
torch_dtype = kwargs.pop("torch_dtype", linear.weight.dtype)
^^^^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'dtype'

Prompt executed in 16.24 seconds
FETCH ComfyRegistry Data: 55/133
FETCH ComfyRegistry Data: 60/133
FETCH ComfyRegistry Data: 65/133
FETCH ComfyRegistry Data: 70/133
FETCH ComfyRegistry Data: 75/133
FETCH ComfyRegistry Data: 80/133
FETCH ComfyRegistry Data: 85/133
FETCH ComfyRegistry Data: 90/133
FETCH ComfyRegistry Data: 95/133
FETCH ComfyRegistry Data: 100/133
FETCH ComfyRegistry Data: 105/133
FETCH ComfyRegistry Data: 110/133
FETCH ComfyRegistry Data: 115/133
FETCH ComfyRegistry Data: 120/133
FETCH ComfyRegistry Data: 125/133
FETCH ComfyRegistry Data: 130/133
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[DONE]
[ComfyUI-Manager] All startup tasks have been completed.
------------------------
Fault Traceback:
Not Available
```

### Other

我的环境：
Microsoft Windows [版本 10.0.19045.6466]
(c) Microsoft Corporation。保留所有权利。

[SD-Launcher] D:\AI\ComfyUI-WorkFisher-V2\ComfyUI>python -c "import torch; print(torch.version)"
2.8.0+cu128

Microsoft Windows [版本 10.0.19045.6466]
(c) Microsoft Corporation。保留所有权利。

C:\Users\Administrator>nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2025 NVIDIA Corporation
Built on Fri_Feb_21_20:42:46_Pacific_Standard_Time_2025
Cuda compilation tools, release 12.8, V12.8.93
Build cuda_12.8.r12.8/compiler.35583870_0

C:\Users\Administrator>dir "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8"
驱动器 C 中的卷没有标签。
卷的序列号是 F813-98A8

C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8 的目录

2026/03/02 17:24

.
2026/03/02 17:24 ..
2026/03/02 17:24 bin
2026/03/02 17:24 compute-sanitizer
2025/02/13 18:16 80,660 CUDA_Toolkit_Release_Notes.txt
2025/02/13 18:16 160 DOCS
2025/02/13 18:16 63,021 EULA.txt
2026/03/02 17:24 extras
2026/03/02 17:24 include
2026/03/02 17:24 lib
2026/03/02 17:24 libnvvp
2025/02/13 18:16 63,021 LICENSE
2026/03/02 17:24 nvml
2026/03/02 17:24 nvvm
2025/02/13 18:16 524 README
2026/03/02 17:24 src
2026/03/02 17:24 tools
2025/03/04 12:48 2,704 version.json
6 个文件 210,090 字节
12 个目录 127,077,294,080 可用字节
C:\Users\Administrator>echo %CUDA_PATH%
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.8

+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 10064 C+G E:\game\QQ新版本安装目录\QQ.exe N/A |
| 0 N/A N/A 11916 C+G D:\Quark\quark.exe N/A |
| 0 N/A N/A 18136 C+G ...5n1h2txyewy\TextInputHost.exe N/A |
| 0 N/A N/A 18924 C+G ...t\Edge\Application\msedge.exe N/A |
| 0 N/A N/A 20496 C+G D:\Quark\quark.exe N/A |
| 0 N/A N/A 22584 C+G ...t\Edge\Application\msedge.exe N/A |
| 0 N/A N/A 23192 C+G ...ntrolPanel\SystemSettings.exe N/A |
| 0 N/A N/A 23464 C+G C:\Windows\explorer.exe N/A |
| 0 N/A N/A 24132 C+G ...h_cw5n1h2txyewy\SearchApp.exe N/A |
+-----------------------------------------------------------------------------------------+
我更新后发现用不了才安装了新的轮子，新轮子提示安装成功的。nunchaku-1.2.1+cu12.8torch2.8-cp312-cp312-win_amd64.whl这个是我用的轮子
D:\AI\ComfyUI-WorkFisher-V2\python>python.exe -m pip list
Package Version

absl-py 2.3.0
accelerate 1.12.0
addict 2.4.0
aiofiles 24.1.0
aiohappyeyeballs 2.6.1
aiohttp 3.12.13
aiohttp-cors 0.8.1
aiohttp_socks 0.10.1
aiosignal 1.3.2
albucore 0.0.24
albumentations 2.0.8
alembic 1.16.2
annotated-types 0.7.0
antlr4-python3-runtime 4.9.3
anyio 4.9.0
argostranslate 1.9.6
attrs 25.3.0
av 14.4.0
beautifulsoup4 4.13.4
bitsandbytes 0.48.1
blake3 1.0.8
blend_modes 2.2.0
blobfile 3.1.0
boto3 1.34.86
botocore 1.34.162
brotli 1.2.0
build 1.4.0
cachetools 6.1.0
certifi 2025.11.12
cffi 2.0.0
cfgv 3.4.0
chardet 5.2.0
charset-normalizer 3.4.4
click 8.2.1
clip-interrogator 0.6.0
cmake 4.1.2
color-matcher 0.6.0
colorama 0.4.6
coloredlogs 15.0.1
colorlog 6.9.0
colour-science 0.4.6
comfy-aimdo 0.2.10
comfy-kitchen 0.2.8
comfyui-embedded-docs 0.4.3
comfyui_frontend_package 1.41.19
comfyui_workflow_templates 0.9.21
comfyui-workflow-templates-core 0.3.168
comfyui-workflow-templates-media-api 0.3.64
comfyui-workflow-templates-media-image 0.3.104
comfyui-workflow-templates-media-other 0.3.141
comfyui-workflow-templates-media-video 0.3.60
contourpy 1.3.2
cryptography 46.0.3
cssselect2 0.8.0
cstr 0.1.0
ctranslate2 4.6.0
cupy-cuda12x 13.6.0
cycler 0.12.1
Cython 3.1.2
datasets 4.4.2
ddgs 9.10.0
ddt 1.7.2
decord 0.6.0
deep-translator 1.11.4
deepdiff 8.6.1
Deprecated 1.2.18
diffusers 0.36.0
dill 0.4.0
diskcache 5.6.3
distlib 0.4.0
distro 1.9.0
dlib 19.24.99
docstring_parser 0.17.0
docutils 0.21.2
dotenv 0.9.9
easydict 1.13
einops 0.8.1
einx 0.3.0
et_xmlfile 2.0.0
facexlib 0.3.0
fairscale 0.4.13
fake-useragent 2.2.0
fal_client 0.8.1
faster-whisper 1.2.0
fastrlock 0.8.3
ffmpy 0.3.0
filelock 3.20.1
filterpy 1.4.5
flatbuffers 25.2.10
fonttools 4.58.4
frozendict 2.4.7
frozenlist 1.7.0
fsspec 2025.10.0
ftfy 6.1.1
future 1.0.0
fvcore 0.1.5.post20221221
gdown 5.2.0
geographiclib 2.1
geopy 2.4.1
gguf 0.17.1
gitdb 4.0.12
GitPython 3.1.44
glfw 2.10.0
googletrans-py 4.0.0
greenlet 3.2.3
groundingdino-py 0.4.0
h11 0.16.0
h2 4.2.0
hf_transfer 0.1.9
hf-xet 1.2.0
hpack 4.1.0
httpcore 1.0.9
httpx 0.28.1
httpx-sse 0.4.3
huggingface-hub 0.36.0
humanfriendly 10.0
hydra-core 1.3.2
hyperframe 6.1.0
identify 2.6.15
idna 3.11
imageio 2.37.0
imageio-ffmpeg 0.6.0
img2texture 1.0.6
importlib_metadata 8.7.0
iniconfig 2.3.0
insightface 0.7.3
instructor 1.11.3
iopath 0.1.10
jax 0.6.2
jaxlib 0.6.2
Jinja2 3.1.6
jiter 0.10.0
jmespath 1.0.1
joblib 1.5.1
json_repair 0.52.3
jsonschema 4.24.0
jsonschema-specifications 2025.4.1
kagglehub 0.4.1
kagglesdk 0.1.15
kaldi-native-fbank 1.22.3
kiwisolver 1.4.8
kornia 0.8.1
kornia_rs 0.1.9
lark 1.3.0
lark-parser 0.12.0
lazy_loader 0.4
lightning-utilities 0.15.2
llama_cpp_python 0.3.18
llvmlite 0.45.1
loguru 0.7.3
loralib 0.1.2
lxml 6.0.0
Mako 1.3.10
manifold3d 3.1.1
mapbox_earcut 1.0.3
markdown-it-py 3.0.0
MarkupSafe 3.0.3
matplotlib 3.10.3
matrix-client 0.4.0
matrix-nio 0.25.2
mdurl 0.1.2
mediapipe 0.10.21
ml_dtypes 0.5.1
modelscope 1.33.0
mpmath 1.3.0
mss 10.0.0
multidict 6.6.2
multiprocess 0.70.18
natsort 8.4.0
nest-asyncio 1.6.0
networkx 3.3
ninja 1.11.1.4
nodeenv 1.9.1
ntplib 0.4.0
numba 0.62.1
numpy 1.26.4
nunchaku 1.2.1+cu12.8torch2.8
nvidia-ml-py 13.580.82
ollama 0.6.0
omegaconf 2.3.0
onnx 1.18.0
onnxruntime 1.22.0
onnxruntime-gpu 1.22.0
open_clip_torch 3.2.0
openai 1.109.1
opencv-contrib-python 4.8.0.76
opencv-contrib-python-headless 4.11.0.86
opencv-python 4.8.0.76
opencv-python-headless 4.9.0.80
openpyxl 3.1.5
opt_einsum 3.4.0
optimum 2.1.0
orderly-set 5.5.0
packaging 25.0
pandas 2.3.3
peft 0.17.0
piexif 1.1.3
pilgram 1.2.1
pillow 12.0.0
pip 25.3
pipdeptree 2.30.0
pixeloe 0.1.4
platformdirs 4.3.8
pluggy 1.6.0
polars 1.34.0
polars-runtime-32 1.34.0
pooch 1.8.2
portalocker 3.2.0
pre_commit 4.3.0
prettytable 3.16.0
primp 0.15.0
propcache 0.3.2
protobuf 4.25.8
psutil 7.0.0
py-cpuinfo 9.0.0
pyarrow 22.0.0
pycocotools 2.0.10
pycollada 0.9.1
pycparser 2.22
pycryptodome 3.23.0
pycryptodomex 3.23.0
pydantic 2.11.7
pydantic_core 2.33.2
pydantic-settings 2.10.1
PyGithub 2.6.1
Pygments 2.19.2
PyJWT 2.10.1
pyloudnorm 0.1.1
PyMatting 1.1.14
PyNaCl 1.5.0
pynvml 13.0.1
PyOpenGL 3.1.10
PyOpenGL-accelerate 3.1.10
pyOpenSSL 25.3.0
pyparsing 3.2.3
pyproject_hooks 1.2.0
pyreadline3 3.5.4
PySocks 1.7.1
pytest 8.4.2
python-dateutil 2.9.0.post0
python-dotenv 1.1.1
python-socks 2.7.1
pytorch-extension 0.2
pytorch-lightning 2.5.5
pytz 2025.2
PyWavelets 1.9.0
pywin32 310
PyYAML 6.0.3
qwen-vl-utils 0.0.14
redis 7.1.0
referencing 0.36.2
regex 2025.11.3
rembg 2.0.66
replicate 1.0.7
reportlab 4.4.2
requests 2.32.5
rich 14.0.0
rotary-embedding-torch 0.8.9
rpds-py 0.25.1
rtree 1.4.0
s3transfer 0.10.4
sacremoses 0.0.53
safetensors 0.7.0
sageattention 2.2.0+cu128torch2.8.0
SAM-2 1.0
scenedetect 0.6.7.1
scikit-image 0.25.2
scikit-learn 1.7.0
scipy 1.16.0
segment-anything 1.0
sentencepiece 0.2.0
setuptools 80.9.0
shapely 2.1.1
shellingham 1.5.4
simpleeval 1.0.4
simsimd 6.4.9
six 1.17.0
smmap 5.0.2
sniffio 1.3.1
socksio 1.0.0
sounddevice 0.5.2
soundfile 0.13.1
soupsieve 2.7
spandrel 0.4.1
SQLAlchemy 2.0.41
stanza 1.1.1
stringzilla 3.12.5
supervision 0.6.0
surrealist 1.1.2
svg.path 6.3
svglib 1.5.1
swarm 0.1.0
sympy 1.13.3
tabulate 0.9.0
tenacity 9.1.2
termcolor 3.1.0
threadpoolctl 3.6.0
tifffile 2025.6.11
tiktoken 0.12.0
timm 1.0.19
tinycss2 1.4.0
tokenizers 0.22.2
toml 0.10.2
tomli 2.2.1
torch 2.8.0+cu128
torchao 0.15.0
torchaudio 2.8.0+cu128
torchcodec 0.10.0
torchdata 0.11.0
torchmetrics 1.8.2
torchsde 0.2.6
torchtune 0.6.1
torchvision 0.23.0+cu128
tqdm 4.67.1
trampoline 0.1.2
transformers 4.57.3
transparent-background 1.3.4
trimesh 4.6.13
triton-windows 3.5.1.post23
typer 0.16.0
typing_extensions 4.15.0
typing-inspection 0.4.1
tzdata 2025.3
ultralytics 8.3.221
ultralytics-thop 2.0.17
unpaddedbase64 2.1.0
urllib3 1.26.20
uv 0.7.17
vector-quantize-pytorch 1.27.20
vhacdx 0.0.8.post2
virtualenv 20.35.3
watchdog 6.0.0
wcwidth 0.2.14
webcolors 24.11.1
webencodings 0.5.1
websocket-client 1.9.0
wget 3.2
wheel 0.45.1
win32_setctime 1.2.0
wrapt 1.17.2
xxhash 3.5.0
yacs 0.1.8
yapf 0.43.0
yarl 1.20.1
zipp 3.23.0
————————————————————————————————————————————————————————

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

AttributeError: 'NoneType' object has no attribute 'dtype'我不懂为什么以前能用nunchaku出图，现在更新了comfyui后，反而用不了

Description

Contributor guide

Assessment

Get new issues in your inbox