Open Shangooriginal opened 3 months ago
Hi. seems you didn't install nvdiffrast
Please follow the install instruction and if you are using windows python3.11 & cuda 12.1 then make sure all the wheels are installed
Hi. seems you didn't install nvdiffrast
Please follow the install instruction and if you are using windows python3.11 & cuda 12.1 then make sure all the wheels are installed
How do you install a wheel with Python ? I have a big wrench, not sure how to use it on the PC. Your link is dead by the way. I have Python 3.10.11+Cuda 12.1, not good ?
you can install wheel like this :
If it's say is already installed do this:
Same error I reinstall nvdiffrast and get the error everything else work ok only problem. Error occurred when executing [Comfy3D] Load Convolutional Reconstruction Model:
DLL load failed while importing nvdiffrast_plugin: The specified module could not be found.
File "K:\ComfyUI\ComfyUI_Ex\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\ComfyUI\custom_nodes\ComfyUI-3D-Pack\nodes.py", line 1898, in load_CRM crm_model = CRM(crm_conf).to(device) ^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\ComfyUI\custom_nodes\ComfyUI-3D-Pack\crm\model\crm\model.py", line 59, in init self.renderer = Renderer(tet_grid_size=self.tet_grid_size, camera_angle_num=self.camera_angle_num, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\ComfyUI\custom_nodes\ComfyUI-3D-Pack\crm\util\renderer.py", line 15, in init self.glctx = dr.RasterizeCudaContext() ^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\python_miniconda_env\ComfyUI\Lib\site-packages\nvdiffrast\torch\ops.py", line 177, in init self.cpp_wrapper = _get_plugin().RasterizeCRStateWrapper(cuda_device_idx) ^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\python_miniconda_env\ComfyUI\Lib\site-packages\nvdiffrast\torch\ops.py", line 118, in _get_plugin torch.utils.cpp_extension.load(name=plugin_name, sources=source_paths, extra_cflags=opts, extra_cuda_cflags=opts+['-lineinfo'], extra_ldflags=ldflags, with_cuda=True, verbose=False) File "K:\ComfyUI\ComfyUI_Ex\python_miniconda_env\ComfyUI\Lib\site-packages\torch\utils\cpp_extension.py", line 1306, in load return _jit_compile( ^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\python_miniconda_env\ComfyUI\Lib\site-packages\torch\utils\cpp_extension.py", line 1736, in _jit_compile return _import_module_from_library(name, build_directory, is_python_module) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "K:\ComfyUI\ComfyUI_Ex\python_miniconda_env\ComfyUI\Lib\site-packages\torch\utils\cpp_extension.py", line 2132, in _import_module_from_library module = importlib.util.module_from_spec(spec) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "", line 573, in module_from_spec File "", line 1233, in create_module File "", line 241, in _call_with_frames_removed
I'm having the same error, my ComfyUI install is through Pinokio so it may be a problem of path at the requirements_post step or something because Pinokio is using its own venv system I think. Python and Torch CUDA are installed properly, it's failing just after the CRM model loading, I guess when it tries to build the mesh (which is quite frustrating because everything worked fine until this point, images look very nice).
Trying again, failing again, tumbling on the same post as last month, no improvement, only frustration. Sad stuff
Tried to fix with uninstalling and re-installing it to no avail. Can anyone help?
Error occurred when executing [Comfy3D] Load Convolutional Reconstruction Model:
DLL load failed while importing nvdiffrast_plugin: The specified module could not be found.
File "C:\Users\xxxx\Downloads\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxxx\Downloads\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxxx\Downloads\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxxx\Downloads\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-3D-Pack\nodes.py", line 1898, in load_CRM crm_model = CRM(crm_conf).to(device) ^^^^^^^^^^^^^ File "C:\Users\xxxx\Downloads\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-3D-Pack\crm\model\crm\model.py", line 59, in init self.renderer = Renderer(tet_grid_size=self.tet_grid_size, camera_angle_num=self.camera_angle_num, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxxx\Downloads\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-3D-Pack\crm\util\renderer.py", line 15, in init self.glctx = dr.RasterizeCudaContext() ^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxxx\Downloads\ComfyUI_windows_portable\python_embeded\Lib\site-packages\nvdiffrast\torch\ops.py", line 177, in init self.cpp_wrapper = _get_plugin().RasterizeCRStateWrapper(cuda_device_idx) ^^^^^^^^^^^^^ File "C:\Users\xxxx\Downloads\ComfyUI_windows_portable\python_embeded\Lib\site-packages\nvdiffrast\torch\ops.py", line 118, in _get_plugin torch.utils.cpp_extension.load(name=plugin_name, sources=source_paths, extra_cflags=opts, extra_cuda_cflags=opts+['-lineinfo'], extra_ldflags=ldflags, with_cuda=True, verbose=False) File "C:\Users\xxxx\Downloads\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils\cpp_extension.py", line 1306, in load return _jit_compile( ^^^^^^^^^^^^^ File "C:\Users\xxxx\Downloads\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils\cpp_extension.py", line 1736, in _jit_compile return _import_module_from_library(name, build_directory, is_python_module) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxxx\Downloads\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils\cpp_extension.py", line 2132, in _import_module_from_library module = importlib.util.module_from_spec(spec) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "", line 573, in module_from_spec File "", line 1233, in create_module File "", line 241, in _call_with_frames_removed