aswordok

``` Loading 3 new models 100%|████████████████████████████████████████████████████████████████████████████████████| 6/6 [00:23

Can you say clear. use this node?: https://github.com/liusida/ComfyUI-Debug @AInseven

"C:\Users\user\AppData\Local\Programs\Python\Python311\Lib\site-packages\nvidia\cuda_nvrtc\bin\nvrtc64_120_0.dll" copy it to : C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\bin Confirm your Path and modify it.

打开 "D:\+AI\myComfyUI\ComfyUI\custom_nodes\comfyui_fk_server\server.py"，备注掉最后一个模块，从 if pzdata: 开始，到结束全部备注掉。 那个云算力估计你也用不上。我也是只用到它的深度翻译节点。

win11: cd D:+AI\comfyUI\ComfyUI_windows_portable\python_embeded 1. python -m pip install --pre --upgrade torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu124 Successfully installed torch-2.4.0.dev20240606+cu124 torchaudio-2.2.0.dev20240606+cu124 torchvision-0.19.0.dev20240606+cu124 2. from : https://visualstudio.microsoft.com/zh-hans/visual-cpp-build-tools/ , download & install the first...

> > win11: cd D:+AI\comfyUI\ComfyUI_windows_portable\python_embeded 1. python -m pip install --pre --upgrade torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu124 Successfully installed torch-2.4.0.dev20240606+cu124 torchaudio-2.2.0.dev20240606+cu124 torchvision-0.19.0.dev20240606+cu124 2. from : https://visualstudio.microsoft.com/zh-hans/visual-cpp-build-tools/ , download & install...

> > win11: cd D:+AI\comfyUI\ComfyUI_windows_portable\python_embeded 1. python -m pip install --pre --upgrade torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu124 Successfully installed torch-2.4.0.dev20240606+cu124 torchaudio-2.2.0.dev20240606+cu124 torchvision-0.19.0.dev20240606+cu124 2. from : https://visualstudio.microsoft.com/zh-hans/visual-cpp-build-tools/ , download & install...

windows 下： 手工安装两种方法解决： 打开 ImageReward 的 README.md ，另存为 ansi。 另一种解决方法是打开 ImageReward 的 setup.py 修改这一行 long_description = (Path(__file__).parent / "README.md").read_text() 中的.read_text()为.read_text(encoding="utf-8") 直接 pip install image-reward 安装仍然出错，没法解决。

@doctorpangloss wsl is not necessary. if you get 'fused_layer_norm_cuda' error, just build with --cuda_ext.

Windows 11 + python 3.12.10 + torch 2.7.0 + cuda 12.8 + flash-attention v2.7.4.post1，测试同样编译通过。