Closed cmd-d closed 8 months ago
Have you install via pip install custom_nodes/ComfyUI-OOTDiffusion/requirements.txt
?
What is your diffusers version? (pip freeze
)
C:\Users\User>python -c "import diffusers; print(diffusers.version)" 0.24.0
And, sure, I have pip install -r requirements.txt
Run where python
. I think you are using system python to install dependencies but use ComfyUI embeded python to run ComfyUI (via .bat
file).
Ok, so, I tried installing from ...\python_embeded\python -m pip install [requirements file] However, now it is not loading Comfty. Here is my current setup, I really don't get what am I doing wrong.
C:\Users\User\Comfty\ComfyUI_windows_portable\python_embeded>nvcc --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2022 NVIDIA Corporation Built on Wed_Sep_21_10:41:10_Pacific_Daylight_Time_2022 Cuda compilation tools, release 11.8, V11.8.89 Build cuda_11.8.r11.8/compiler.31833905_0
C:\Users\User\Comfty\ComfyUI_windows_portable\python_embeded>pip freeze absl-py==2.1.0 accelerate==0.27.2 addict==2.4.0 aiofiles==23.2.1 aiohttp==3.9.3 aiosignal==1.3.1 albumentations==1.3.1 altair==5.2.0 annotated-types==0.6.0 antlr4-python3-runtime==4.9.3 anyio==4.3.0 astroid==2.15.0 async-timeout==4.0.3 attrs==23.2.0 autopep8==1.6.0 bidict==0.22.1 blinker==1.6.2 cachetools==5.3.3 cchardet==2.1.7 certifi==2024.2.2 cffi==1.16.0 cfgv==3.3.1 charset-normalizer==3.3.2 click==8.1.7 cmake==3.28.1 colorama==0.4.6 coloredlogs==15.0.1 colour-science==0.4.4 contourpy==1.2.0 cstr @ git+https://github.com/WASasquatch/cstr@0520c29a18a7a869a6e5983861d6f7a4c86f8e9b cycler==0.12.1 Cython==3.0.2 diffusers==0.26.0 dill==0.3.7 distlib==0.3.6 docstring-to-markdown==0.11 easydict==1.10 einops==0.7.0 exceptiongroup==1.2.0 fairscale==0.4.13 fastapi==0.110.0 ffmpy @ git+https://github.com/WASasquatch/ffmpy.git@f000737698b387ffaeab7cd871b0e9185811230d filelock==3.13.1 flake8==6.0.0 Flask==2.3.2 Flask-SocketIO==5.3.4 flatbuffers==23.5.26 fonttools==4.49.0 frozenlist==1.4.1 fsspec==2024.2.0 gitdb==4.0.11 GitPython==3.1.42 google-ai-generativelanguage==0.4.0 google-api-core==2.17.1 google-auth==2.28.2 google-generativeai==0.4.0 googleapis-common-protos==1.63.0 gradio==4.16.0 gradio_client==0.8.1 grpcio==1.62.1 grpcio-status==1.48.2 h11==0.14.0 httpcore==1.0.4 httpx==0.27.0 huggingface-hub==0.21.4 humanfriendly==10.0 identify==2.5.24 idna==3.6 imageio==2.34.0 img2texture @ git+https://github.com/WASasquatch/img2texture.git@a546609a915caf1dcb84a15bf44b5b639ad924e6 importlib-metadata==7.0.1 importlib_resources==6.1.2 insightface==0.7.3 install==1.3.5 isort==5.12.0 itsdangerous==2.1.2 jax==0.4.25 jedi==0.18.2 jieba==0.42.1 Jinja2==3.1.3 joblib==1.3.2 jsonschema==4.21.1 jsonschema-specifications==2023.12.1 kiwisolver==1.4.5 lazy-object-proxy==1.9.0 lazy_loader==0.3 llvmlite==0.42.0 loguru==0.7.2 Markdown==3.4.4 markdown-it-py==3.0.0 MarkupSafe==2.1.5 matplotlib==3.8.3 mccabe==0.7.0 mdurl==0.1.2 mediapipe==0.10.11 ml-dtypes==0.3.2 mpmath==1.3.0 multidict==6.0.5 multiprocess==0.70.15 networkx==3.2.1 ninja==1.11.1.1 nodeenv==1.8.0 numba==0.59.0 numpy==1.24.4 nvidia-ml-py3==7.352.0 omegaconf==2.3.0 onnx==1.14.1 onnxruntime==1.17.1 openai==0.27.8 opencv-contrib-python==4.9.0.80 opencv-python==4.7.0.72 opencv-python-headless==4.7.0.72 opt-einsum==3.3.0 orjson==3.9.15 packaging==24.0 pandas==2.2.1 parso==0.8.3 pilgram==1.2.1 Pillow==9.5.0 platformdirs==3.5.3 pluggy==1.2.0 pooch==1.8.1 pre-commit==3.3.3 prettytable==3.8.0 proto-plus==1.23.0 protobuf==3.20.3 psutil==5.9.8 pyarrow==13.0.0 pyasn1==0.5.1 pyasn1-modules==0.3.0 pycodestyle==2.10.0 pycparser==2.21 pydantic==2.6.3 pydantic_core==2.16.3 pydocstyle==6.2.3 pydub==0.25.1 pyflakes==3.0.1 pygame==2.5.1 pygit==0.1 pygit2==1.14.1 Pygments==2.17.2 pylint==2.17.0 PyMatting==1.1.12 pyparsing==3.1.2 pyreadline3==3.4.1 PySocks==1.7.1 python-dateutil==2.9.0.post0 python-engineio==4.5.1 python-lsp-jsonrpc==1.0.0 python-lsp-server==1.7.1 python-multipart==0.0.9 python-socketio==5.8.0 pytoolconfig==1.2.5 pytz==2024.1 PyWavelets==1.4.1 PyYAML==6.0.1 qudida==0.0.4 referencing==0.33.0 regex==2023.12.25 rembg==2.0.55 requests==2.31.0 retrying==1.3.4 rich==13.7.1 rope==1.7.0 rpds-py==0.18.0 rsa==4.9 ruff==0.3.0 safetensors==0.4.2 scikit-image==0.20.0 scikit-learn==1.3.0 scipy==1.12.0 segment-anything==1.0 semantic-version==2.10.0 shellingham==1.5.4 six==1.16.0 smmap==5.0.1 sniffio==1.3.1 snowballstemmer==2.2.0 sounddevice==0.4.6 starlette==0.36.3 sympy==1.12 tenacity==8.2.2 threadpoolctl==3.2.0 tifffile==2024.2.12 tiktoken==0.4.0 timeout-decorator==0.5.0 timm==0.9.16 tokenizers==0.13.3 toml==0.10.2 tomli==2.0.1 tomlkit==0.12.0 toolz==0.12.1 torch==2.0.1+cu118 torchaudio==2.0.2+cu118 torchsde==0.2.6 torchvision==0.15.2+cu118 tqdm==4.66.2 trampoline==0.1.2 transformers==4.26.1 typer==0.9.0 typer-config==1.4.0 typing_extensions==4.10.0 tzdata==2024.1 ujson==5.7.0 urllib3==2.2.1 uvicorn==0.27.1 virtualenv==20.23.0 wcwidth==0.2.6 websockets==11.0.3 Werkzeug==2.3.6 wget==3.2 whatthepatch==1.0.4 win32-setctime==1.1.0 wrapt==1.15.0 xxhash==3.3.0 yapf==0.32.0 yarl==1.9.4 zipp==3.17.0
look this issue
Do you see your diffusers==0.26.0
which is incompatible with diffusers==0.24.0
? It is a issue about your environment management.
Use conda and start ComfyUI via conda activate <env>
and python main.py
manually.
this error may be because of : Ninja is required to load C++ extensions. Check in your compfyui terminal
(IMPORT FAILED): C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-OOTDiffusion
File "C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1887, in load_custom_node module_spec.loader.exec_module(module) File "", line 940, in exec_module
File "", line 241, in _call_with_frames_removed
File "C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-OOTDiffusion__init__.py", line 10, in
from .inference_ootd import OOTDiffusion
File "C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-OOTDiffusion\inference_ootd.py", line 23, in
from .pipelines_ootd.pipeline_ootd import OotdPipeline
File "C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-OOTDiffusion\pipelines_ootd\pipeline_ootd.py", line 27, in
from .unet_vton_2d_condition import UNetVton2DConditionModel
File "C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-OOTDiffusion\pipelines_ootd\unet_vton_2d_condition.py", line 23, in
from .unet_vton_2d_blocks import (
File "C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-OOTDiffusion\pipelines_ootd\unet_vton_2d_blocks.py", line 23, in
from .transformer_vton_2d import Transformer2DModel
File "C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-OOTDiffusion\pipelines_ootd\transformer_vton_2d.py", line 23, in
from .attention_vton import BasicTransformerBlock
File "C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-OOTDiffusion\pipelines_ootd\attention_vton.py", line 21, in
from diffusers.utils import USE_PEFT_BACKEND
ImportError: cannot import name 'USE_PEFT_BACKEND' from 'diffusers.utils' (C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\utils__init__.py)
Cannot import C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-OOTDiffusion module for custom nodes: cannot import name 'USE_PEFT_BACKEND' from 'diffusers.utils' (C:\Users\User\Comfty\ComfyUI_windows_portable_nvidia_cu121\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\utils__init__.py)