Tencent
Hy3DRenderMultiView - DLL load failed while importing custom_rasterizer_kernel: The specified procedure could not be found.
Can someone help me with this?
D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build [START] Security scan [DONE] Security scan
ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2025-02-19 20:34:49.195 ** Platform: Windows ** Python version: 3.12.8 (tags/v3.12.8:2dc476b, Dec 3 2024, 19:30:04) [MSC v.1942 64 bit (AMD64)] ** Python executable: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\python.exe ** ComfyUI Path: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI ** ComfyUI Base Folder Path: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI ** User directory: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\user ** ComfyUI-Manager config path: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Manager\config.ini ** Log path: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\user\comfyui.log
Prestartup times for custom nodes: 3.1 seconds: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-manager
Checkpoint files will always be loaded safely. Total VRAM 24576 MB, total RAM 130702 MB pytorch version: 2.6.0+cu126 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync Using pytorch attention ComfyUI version: 0.3.14 [Prompt Server] web root: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\web
Loading: ComfyUI-Manager (V3.25.1)
[ComfyUI-Manager] network_mode: public
ComfyUI Revision: 3109 [debabccb] *DETACHED | Released on '2025-02-05'
Import times for custom nodes: 0.0 seconds: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py 0.0 seconds: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_essentials 0.5 seconds: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-manager 1.3 seconds: D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Hunyuan3DWrapper
Starting server
To see the GUI go to: http://127.0.0.1:8188
[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/model-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/custom-node-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
got prompt
FETCH ComfyRegistry Data: 5/34
D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\albumentations_init_.py:13: UserWarning: A new version of Albumentations is available: 2.0.4 (you have 1.4.15). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1.
check_for_updates()
D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\timm\models\layers_init_.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
warnings.warn(f"Importing from {name} is deprecated, please import via timm.layers", FutureWarning)
D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\functional.py:539: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at C:\actions-runner_work\pytorch\pytorch\pytorch\aten\src\ATen\native\TensorShape.cpp:3638.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Settings -> Mode=base, Device=cuda:0, Torchscript=enabled
Loading pipeline components...: 33%|█████████████████▎ | 2/6 [00:00<00:00, 6.10it/s]FETCH ComfyRegistry Data: 10/34
Loading pipeline components...: 100%|████████████████████████████████████████████████████| 6/6 [00:03<00:00, 1.80it/s]
FETCH ComfyRegistry Data: 15/34
FETCH ComfyRegistry Data: 20/34
D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torchvision\transforms\v2_deprecated.py:42: UserWarning: The transform ToTensor() is deprecated and will be removed in a future release. Instead, please use v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)]).Output is equivalent up to float precision.
warnings.warn(
Loading model from D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\models\diffusion_models\hy3dgen\hunyuan3d-dit-v2-0-fp16.safetensors
FETCH ComfyRegistry Data: 25/34
FETCH ComfyRegistry Data: 30/34
guidance: None
Diffusion Sampling:: 12%|███████▍ | 6/50 [00:02<00:17, 2.57it/s]FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
nightly_channel: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/remote
Diffusion Sampling:: 14%|████████▋ | 7/50 [00:02<00:17, 2.41it/s] [DONE]
[ComfyUI-Manager] All startup tasks have been completed.
Diffusion Sampling:: 100%|█████████████████████████████████████████████████████████████| 50/50 [00:21<00:00, 2.37it/s]
latents shape: torch.Size([1, 3072, 64])
Allocated memory: memory=2.428 GB
Max allocated memory: max_memory=4.611 GB
Max reserved memory: max_reserved=4.656 GB
MC Level 0.0 Implicit Function:: 100%|████████████████████████████████████████████| 7134/7134 [00:52<00:00, 135.01it/s]
Decoded mesh with 216205 vertices and 432396 faces
Removed floaters, resulting in 216161 vertices and 432318 faces
Removed degenerate faces, resulting in 216161 vertices and 432318 faces
Reduced faces, resulting in 25002 vertices and 50000 faces
camera_distance: 1.45
!!! Exception during processing !!! DLL load failed while importing custom_rasterizer_kernel: The specified procedure could not be found.
Traceback (most recent call last):
File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 327, 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 202, 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 174, in map_node_over_list
process_inputs(input_dict, i)
File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Hunyuan3DWrapper\nodes.py", line 433, in process
self.render = MeshRender(
^^^^^^^^^^^
File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Hunyuan3DWrapper\hy3dgen\texgen\differentiable_renderer\mesh_render.py", line 158, in init
import custom_rasterizer as cr
File "D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\custom_rasterizer_init.py", line 32, in
Prompt executed in 126.04 seconds
Same for me, the whole compiling thing is a headache so I found some zipped custom_rasterizer in another post, from there it's now missing custom_rasterizer_kernel. I tried a fresh ComfyUI_portable, it's now using Python 3.12 instead of 3.11 so I had some hope, but still no luck
And reposting this once again... 3rd time's the charm :v : Just follow the instructions in this comment to the letter (this setup is specifically for ComfyUI so you might be able to skip some stuff and you should adapt it to your own setup's local python installation) : https://github.com/kijai/ComfyUI-Hunyuan3DWrapper/issues/92#issuecomment-2727135940
Warning : Also there might be an issue with the installation of cuda 12.6 where it gets stuck on nsight extention installation for whatever reason (you might not even need that part of cuda 12.6 but I don't know), in that case, just try to install cuda 12.8 instead, worked fine for me.
There will be a bunch of tricky things to install like Visual Studio Build Tools (if you're not sure what to choose, just download visual studio installer, after opening the installer, uncheck all of the stuff that you don't need then go to the Individual Components tab, search for "visual c++ x64 build tools latest" and it should be first result that you should put a checkmark on), but if you follow every instruction properly, it should work.
