Trying to get comfyui to work with a AMD Ryzen 9 5950X with 128 GB of RAM and a Intel B580 running on Windows 11, with out ERRORS

### 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

First time running python main.py and receiving no errors.

### Actual Behavior

First let me say, that the instructions to install comfyui manually are different on https://github.com/comfyanonymous/ComfyUI from the ones on https://docs.comfy.org/installation/manual_install. that may be the problem. I used the instructions on https://github.com/comfyanonymous/ComfyUI.
They do not generate run.bat files so I had to google how to start it with out them.
Part of the problem is me I am sure. I tried to install to a different drive, so I could just delete the folder and start over. I first tried https://github.com/comfyanonymous/ComfyUI/releases with the pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/xpu but that got errors. So I deleted the folder. then I tried a fork, https://github.com/YanWenKun/ComfyUI-WinPortable-XPU, I got less errors. I deleted the folder. I then did the complete manual install from https://github.com/comfyanonymous/ComfyUI#manual-install-windows-linux
I have run "python main.py" and have got errors. I believe that parts of the previous attempts have been installing on my C drive and not on the drive and folder I was trying to install it to . Some times programs install to folders inside the User folder, when that happens it is almost impossible to uninstall them and start over.

Last to say I am 68 years old and trying to learn AI. I don't know any programing. The last time I used cli commands was from Dos.

### Steps to Reproduce

Install in the order from above, then run "python main.py". you should see.

H:\AI\comfyui>python main.py
Checkpoint files will always be loaded safely.
[W902 09:11:21.000000000 OperatorEntry.cpp:225] Warning: Warning only once for all operators, other operators may also be overridden.
Overriding a previously registered kernel for the same operator and the same dispatch key
operator: aten::geometric_(Tensor(a!) self, float p, *, Generator? generator=None) -> Tensor(a!)
registered at C:\actions-runner\_work\pytorch\pytorch\pytorch\build\aten\src\ATen\RegisterSchema.cpp:6
dispatch key: XPU
previous kernel: registered at C:\actions-runner\_work\pytorch\pytorch\pytorch\aten\src\ATen\VmapModeRegistrations.cpp:37
new kernel: registered at E:\frameworks.ai.pytorch.ipex-gpu\build\Release\csrc\gpu\csrc\gpu\xpu\ATen\RegisterXPU_0.cpp:172 (function operator ())
Total VRAM 11870 MB, total RAM 130997 MB
pytorch version: 2.8.0+xpu
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.8.0+cu128 with CUDA 1208 (you have 2.8.0+xpu)
Python 3.9.13 (you have 3.13.7)
Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
Memory-efficient attention, SwiGLU, sparse and more won't be available.
Set XFORMERS_MORE_DETAILS=1 for more details
Set vram state to: NORMAL_VRAM
Device: xpu:0 Intel(R) Arc(TM) B580 Graphics
Using pytorch attention
Python version: 3.13.7 (tags/v3.13.7:bcee1c3, Aug 14 2025, 14:15:11) [MSC v.1944 64 bit (AMD64)]
ComfyUI version: 0.3.56
****** User settings have been changed to be stored on the server instead of browser storage. ******
****** For multi-user setups add the --multi-user CLI argument to enable multiple user profiles. ******
ComfyUI frontend version: 1.25.11
[Prompt Server] web root: C:\Users\lost_\AppData\Local\Programs\Python\Python313\Lib\site-packages\comfyui_frontend_package\static

Import times for custom nodes:
0.0 seconds: H:\AI\comfyui\custom_nodes\websocket_image_save.py

Context impl SQLiteImpl.
Will assume non-transactional DDL.
No target revision found.
Starting server

To see the GUI go to: http://127.0.0.1:8188
Exception in callback _ProactorBasePipeTransport._call_connection_lost()
handle:
Traceback (most recent call last):
File "C:\Users\lost_\AppData\Local\Programs\Python\Python313\Lib\asyncio\events.py", line 89, in _run
self._context.run(self._callback, *self._args)
~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\lost_\AppData\Local\Programs\Python\Python313\Lib\asyncio\proactor_events.py", line 165, in _call_connection_lost
self._sock.shutdown(socket.SHUT_RDWR)
~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host
Exception in callback _ProactorBasePipeTransport._call_connection_lost()
handle:
Traceback (most recent call last):
File "C:\Users\lost_\AppData\Local\Programs\Python\Python313\Lib\asyncio\events.py", line 89, in _run
self._context.run(self._callback, *self._args)
~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\lost_\AppData\Local\Programs\Python\Python313\Lib\asyncio\proactor_events.py", line 165, in _call_connection_lost
self._sock.shutdown(socket.SHUT_RDWR)
~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host
got prompt
model weight dtype torch.float16, manual cast: None
model_type EPS
Using pytorch attention in VAE
Using pytorch attention in VAE
VAE load device: xpu:0, offload device: cpu, dtype: torch.bfloat16
CLIP/text encoder model load device: xpu:0, offload device: cpu, current: cpu, dtype: torch.float16
Requested to load SD1ClipModel
loaded completely 10450.5578125 235.84423828125 True
2025-09-02 11:00:14,995 - _logger.py - IPEX - INFO - Currently split master weight for xpu only support sgd
2025-09-02 11:00:14,998 - _logger.py - IPEX - INFO - Conv BatchNorm folding failed during the optimize process.
2025-09-02 11:00:15,000 - _logger.py - IPEX - INFO - Linear BatchNorm folding failed during the optimize process.
2025-09-02 11:00:15,913 - _logger.py - IPEX - INFO - Currently split master weight for xpu only support sgd
2025-09-02 11:00:15,916 - _logger.py - IPEX - INFO - Conv BatchNorm folding failed during the optimize process.
2025-09-02 11:00:15,918 - _logger.py - IPEX - INFO - Linear BatchNorm folding failed during the optimize process.
Requested to load BaseModel
loaded completely 10207.21259765625 1639.406135559082 True
2025-09-02 11:00:16,507 - _logger.py - IPEX - INFO - Currently split master weight for xpu only support sgd
2025-09-02 11:00:16,514 - _logger.py - IPEX - INFO - Conv BatchNorm folding failed during the optimize process.
2025-09-02 11:00:16,519 - _logger.py - IPEX - INFO - Linear BatchNorm folding failed during the optimize process.
100%|███████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 7.21it/s]
Requested to load AutoencoderKL
loaded completely 8282.73876953125 159.55708122253418 True
2025-09-02 11:00:19,889 - _logger.py - IPEX - INFO - Currently split master weight for xpu only support sgd
2025-09-02 11:00:19,903 - _logger.py - IPEX - INFO - Conv BatchNorm folding failed during the optimize process.
2025-09-02 11:00:19,911 - _logger.py - IPEX - INFO - Linear BatchNorm folding failed during the optimize process.
Prompt executed in 6.79 seconds
Exception in callback _ProactorBasePipeTransport._call_connection_lost()
handle:
Traceback (most recent call last):
File "C:\Users\lost_\AppData\Local\Programs\Python\Python313\Lib\asyncio\events.py", line 89, in _run
self._context.run(self._callback, *self._args)
~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\lost_\AppData\Local\Programs\Python\Python313\Lib\asyncio\proactor_events.py", line 165, in _call_connection_lost
self._sock.shutdown(socket.SHUT_RDWR)
~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host

### Debug Logs

```powershell
Where do I find logs at? Or how do I make them from CMD prompt?
```

### Other

I think comfyui is so complex that it needs a way to do a total uninstall. So you can do a clean reinstall. One of the errors was about Transformers, it want me to reinstall them from https://github.com/facebookresearch/xformers but they only make them for the NVidia GPU.