slmonker commented 1 day ago

ComfyUI Error Report

Error Details

Node ID: 3
Node Type: HyVideoSampler
Exception Type: subprocess.CalledProcessError

Exception Message: Command '['C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30133\bin\Hostx64\x64\cl.EXE', 'C:\Users\ADMINI~1\AppData\Local\Temp\tmpnpldo08z\main.c', '/nologo', '/O2', '/LD', '/wd4819', '/ID:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\backends\nvidia\include', '/IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\include', '/IC:\Users\ADMINI~1\AppData\Local\Temp\tmpnpldo08z', '/ID:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Include', '/IC:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30133\include', '/IC:\Program Files (x86)\Windows Kits\10\Include\10.0.19041.0\shared', '/IC:\Program Files (x86)\Windows Kits\10\Include\10.0.19041.0\ucrt', '/IC:\Program Files (x86)\Windows Kits\10\Include\10.0.19041.0\um', '/link', '/LIBPATH:D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\backends\nvidia\lib', '/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\lib\x64', '/LIBPATH:D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\libs', '/LIBPATH:D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\libs', '/LIBPATH:C:\Python311\libs', '/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30133\lib\x64', '/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Lib\10.0.19041.0\ucrt\x64', '/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Lib\10.0.19041.0\um\x64', '/LIBPATH:D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\libs', '/LIBPATH:D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\libs', '/LIBPATH:C:\Python311\libs', '/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30133\lib\x64', '/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Lib\10.0.19041.0\ucrt\x64', '/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Lib\10.0.19041.0\um\x64', 'cuda.lib', '/OUT:C:\Users\ADMINI~1\AppData\Local\Temp\tmpnpldo08z\cuda_utils.cp311-win_amd64.pyd']' returned non-zero exit status 2.

Stack Trace


File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 324, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 199, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 170, in _map_node_over_list
process_inputs(input_dict, i)

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 159, in process_inputs
results.append(getattr(obj, func)(**inputs))
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-HunyuanVideoWrapper\nodes.py", line 634, in process
latents = model["pipe"](
          ^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
       ^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-HunyuanVideoWrapper\hyvideo\diffusion\pipelines\pipeline_hunyuan_video.py", line 507, in __call__
noise_pred = self.transformer(  # For an input image (129, 192, 336) (1, 256, 256)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-HunyuanVideoWrapper\hyvideo\modules\models.py", line 647, in forward
img, txt = block(*double_block_args)
           ^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-HunyuanVideoWrapper\hyvideo\modules\models.py", line 203, in forward
attn = attention(
       ^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-HunyuanVideoWrapper\hyvideo\modules\attention.py", line 126, in attention
x = sageattn_varlen_func(
    ^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\_dynamo\eval_frame.py", line 600, in _fn
return fn(*args, **kwargs)
       ^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-HunyuanVideoWrapper\hyvideo\modules\attention.py", line 24, in sageattn_varlen_func
return sageattn_varlen(q, k, v, cu_seqlens_q, cu_seqlens_kv, max_seqlen_q, max_seqlen_kv)
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\sageattention\core.py", line 189, in sageattn_varlen
q_int8, q_scale, k_int8, k_scale, cu_seqlens_q_scale, cu_seqlens_k_scale = per_block_int8_varlen(q, k, cu_seqlens_q, cu_seqlens_k, max_seqlen_q, max_seqlen_k, sm_scale=sm_scale)
                                                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\sageattention\quant_per_block_varlen.py", line 69, in per_block_int8
quant_per_block_int8_kernel[grid](

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\runtime\jit.py", line 345, in <lambda>
return lambda *args, **kwargs: self.run(grid=grid, warmup=False, *args, **kwargs)
                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\runtime\jit.py", line 607, in run
device = driver.active.get_current_device()
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\runtime\driver.py", line 23, in __getattr__
self._initialize_obj()

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\runtime\driver.py", line 20, in _initialize_obj
self._obj = self._init_fn()
            ^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\runtime\driver.py", line 9, in _create_driver
return actives[0]()
       ^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\backends\nvidia\driver.py", line 412, in __init__
self.utils = CudaUtils()  # TODO: make static
             ^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\backends\nvidia\driver.py", line 90, in __init__
mod = compile_module_from_src(Path(os.path.join(dirname, "driver.c")).read_text(), "cuda_utils")
      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\backends\nvidia\driver.py", line 67, in compile_module_from_src
so = _build(name, src_path, tmpdir, library_dirs(), include_dir, libraries)
     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\runtime\build.py", line 79, in _build
ret = subprocess.check_call(cc_cmd)
      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "subprocess.py", line 413, in check_call

## System Information
- **ComfyUI Version:** v0.3.6-7-gc1b92b7
- **Arguments:** ComfyUI\main.py --windows-standalone-build --fast
- **OS:** nt
- **Python Version:** 3.11.9 (tags/v3.11.9:de54cf5, Apr  2 2024, 10:12:12) [MSC v.1938 64 bit (AMD64)]
- **Embedded Python:** true
- **PyTorch Version:** 2.4.1+cu124
## Devices

- **Name:** cuda:0 NVIDIA GeForce RTX 4090 D : cudaMallocAsync
  - **Type:** cuda
  - **VRAM Total:** 25756696576
  - **VRAM Free:** 7595560558
  - **Torch VRAM Total:** 17918066688
  - **Torch VRAM Free:** 1467682414

## Logs

2024-12-04T01:40:06.660661 - [1mFrom Bmad Custom Nodes[0m2024-12-04T01:40:06.660661 - 2024-12-04T01:40:06.662661 - [92mLoaded 124 nodes:2024-12-04T01:40:06.662661 - 2024-12-04T01:40:06.662661 - + api nodes (14)2024-12-04T01:40:06.663637 - 2024-12-04T01:40:06.663637 - + simple utility nodes (58)2024-12-04T01:40:06.663637 - 2024-12-04T01:40:06.663637 - + CV nodes (50)2024-12-04T01:40:06.663637 - 2024-12-04T01:40:06.663637 - + extension dependent nodes (2)2024-12-04T01:40:06.664637 - 2024-12-04T01:40:06.664637 - [93mNot loaded:2024-12-04T01:40:06.664637 - 2024-12-04T01:40:06.664637 - * color clip ade20k node2024-12-04T01:40:06.664637 - 2024-12-04T01:40:06.665637 - [91mProblems:2024-12-04T01:40:06.665637 - 2024-12-04T01:40:06.665637 - ! No module named 'gray2color'2024-12-04T01:40:06.665637 - 2024-12-04T01:40:06.665637 - [0m2024-12-04T01:40:06.665637 - 2024-12-04T01:40:06.720638 - ------------------------------------------2024-12-04T01:40:06.720638 - 2024-12-04T01:40:06.721638 - [34mComfyroll Studio v1.76 : [92m 175 Nodes Loaded[0m2024-12-04T01:40:06.722637 - 2024-12-04T01:40:06.722637 - ------------------------------------------2024-12-04T01:40:06.722637 - 2024-12-04T01:40:06.722637 - For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md2024-12-04T01:40:06.728637 - 2024-12-04T01:40:06.729637 - For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki2024-12-04T01:40:06.729637 - 2024-12-04T01:40:06.729637 - ------------------------------------------2024-12-04T01:40:06.729637 - 2024-12-04T01:40:06.753637 - [1;35m### [START] ComfyUI AlekPet Nodes [1;34mv1.0.34[0m[1;35m ###[0m2024-12-04T01:40:06.753637 - 2024-12-04T01:40:07.748054 - [92mNode -> ChatGLMNode: [93mChatGLM4TranslateCLIPTextEncodeNode, ChatGLM4TranslateTextNode[0m [92m[Loading] [0m2024-12-04T01:40:07.749053 - 2024-12-04T01:40:07.757053 - [92mNode -> ArgosTranslateNode: [93mArgosTranslateCLIPTextEncodeNode, ArgosTranslateTextNode[0m [92m[Loading] [0m2024-12-04T01:40:07.757053 - 2024-12-04T01:40:07.766054 - [92mNode -> DeepTranslatorNode: [93mDeepTranslatorCLIPTextEncodeNode, DeepTranslatorTextNode[0m [92m[Loading] [0m2024-12-04T01:40:07.766054 - 2024-12-04T01:40:07.772053 - [92mNode -> GoogleTranslateNode: [93mGoogleTranslateCLIPTextEncodeNode, GoogleTranslateTextNode[0m [92m[Loading] [0m2024-12-04T01:40:07.776053 - 2024-12-04T01:40:07.783053 - [92mNode -> ExtrasNode: [93mPreviewTextNode, HexToHueNode, ColorsCorrectNode[0m [92m[Loading] [0m2024-12-04T01:40:07.796054 - 2024-12-04T01:40:07.832053 - [92mNode -> PoseNode: [93mPoseNode[0m [92m[Loading] [0m2024-12-04T01:40:07.844054 - 2024-12-04T01:40:07.995193 - [92mNode -> IDENode: [93mIDENode[0m [92m[Loading] [0m2024-12-04T01:40:07.995193 - 2024-12-04T01:40:08.542693 - [92mNode -> PainterNode: [93mPainterNode[0m [92m[Loading] [0m2024-12-04T01:40:08.542693 - 2024-12-04T01:40:08.543693 - [1;35m### [END] ComfyUI AlekPet Nodes ###[0m2024-12-04T01:40:08.543693 - 2024-12-04T01:40:10.386126 - missing pkgs2024-12-04T01:40:10.386126 - 2024-12-04T01:40:10.387126 - []2024-12-04T01:40:10.387126 - 2024-12-04T01:40:10.439126 - # 😺dzNodes: LayerStyle -> [1;33mCannot 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 [4mhttps://github.com/chflame163/ComfyUI_LayerStyle/issues/5[0m[m2024-12-04T01:40:10.440125 - 2024-12-04T01:40:11.876105 - [36;20m[comfy_mtb] | INFO -> loaded [96m90[0m nodes successfuly[0m 2024-12-04T01:40:11.894770 - FaceDetailer: Model directory already exists2024-12-04T01:40:11.894770 - 2024-12-04T01:40:11.895288 - FaceDetailer: Model already exists2024-12-04T01:40:11.895809 - 2024-12-04T01:40:11.985920 - 2024-12-04T01:40:11.985920 - [92m[rgthree-comfy] Loaded 42 fantastic nodes. 🎉[00m2024-12-04T01:40:11.986920 - 2024-12-04T01:40:11.986920 - 2024-12-04T01:40:12.008919 - Please 'pip install apex'2024-12-04T01:40:12.008919 - 2024-12-04T01:40:12.123453 - [34mWAS Node Suite: [0mBlenderNeko's Advanced CLIP Text Encode found, attempting to enable CLIPTextEncode support.[0m2024-12-04T01:40:12.123453 - 2024-12-04T01:40:12.124117 - [34mWAS Node Suite: [0mCLIPTextEncode (BlenderNeko Advanced + NSP) node enabled under WAS Suite/Conditioning menu.[0m2024-12-04T01:40:12.124117 - 2024-12-04T01:40:13.056540 - [34mWAS Node Suite: [0mOpenCV Python FFMPEG support is enabled[0m2024-12-04T01:40:13.056540 - 2024-12-04T01:40:13.056540 - [34mWAS Node Suite [93mWarning: [0mffmpeg_bin_path is not set in D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui\was_suite_config.json config file. Will attempt to use system ffmpeg binaries if available.[0m2024-12-04T01:40:13.057541 - 2024-12-04T01:40:13.774887 - [34mWAS Node Suite: [0mFinished.[0m [32mLoaded[0m [0m219[0m [32mnodes successfully.[0m2024-12-04T01:40:13.774887 - 2024-12-04T01:40:13.774887 - [3m[93m"Art is not freedom from discipline, but disciplined freedom."[0m[3m - John F. Kennedy[0m 2024-12-04T01:40:13.775888 - 2024-12-04T01:40:13.791887 -

ymuhong commented 1 day ago

I think there may be a line missing in this file: /hyvideo/modules /attention.py. Just add sageattn_varlen_func = None before the try at the beginning of the file.

try:
    from flash_attn.flash_attn_interface import flash_attn_varlen_func
except ImportError:
    flash_attn_varlen_func = None

sageattn_varlen_func = None  #THE MISSING LINE

try:
    from sageattention import sageattn_varlen
    @torch.compiler.disable()
    def sageattn_varlen_func(

slmonker commented 1 day ago

I think there may be a line missing in this file: /hyvideo/modules /attention.py. Just add sageattn_varlen_func = None before the try at the beginning of the file.
try:
    from flash_attn.flash_attn_interface import flash_attn_varlen_func
except ImportError:
    flash_attn_varlen_func = None

sageattn_varlen_func = None  #THE MISSING LINE

try:
    from sageattention import sageattn_varlen
    @torch.compiler.disable()
    def sageattn_varlen_func(

ok i will give a shot

ymuhong commented 1 day ago

I just realized that your issue may be different from the one I was having. The error you got seems to be related to the CUDA utilities and triton.

You could maybe try removing and adding triton:

pip uninstall triton sageattention -y
pip install triton --no-cache-dir
pip install sageattention --no-cache-dir

slmonker commented 1 day ago

I just realized that your issue may be different from the one I was having. The error you got seems to be related to the CUDA utilities and triton.

You could maybe try removing and adding triton:
pip uninstall triton sageattention -y
pip install triton --no-cache-dir
pip install sageattention --no-cache-dir

ok，thanks

kijai commented 1 day ago

It doesn't currently work without flash_attn or sageattention, both are somewhat challenging to install on Windows. This error is from incomplete or missing Triton installation that sageattention uses.

slmonker commented 1 day ago

It doesn't currently work without flash_attn or sageattention, both are somewhat challenging to install on Windows. This error is from incomplete or missing Triton installation that sageattention uses.

It's working with flash-attn(luckily i installed it b4),but the result is kind of horrible…… 31dded7320c5abbd6c46b40cde2f36b9

zejacky commented 8 hours ago

Use the manual from purz. https://purz.notion.site/Get-Windows-Triton-working-for-Mochi-6a0c055e21c84cfba7f1dd628e624e97 Works for me with sageattn. I use pytorch version: 2.5.1+cu124

kijai / ComfyUI-HunyuanVideoWrapper

Command '['C:\\Program Files (x86)\\Microsoft Visual Studio\\2019\\BuildTools\\VC\\Tools\\MSVC\\14.29.30133\\bin\\Hostx64\\x64\\cl.EXE' #1

ComfyUI Error Report

Error Details

Stack Trace