Closed MattRM2 closed 3 months ago
https://github.com/comfyanonymous/ComfyUI/issues/2823
pip uninstall rembg
pip uninstall onnxruntime
pip install rembg[gpu] onnxruntime-gpu
This gets rid of the error but no idea how to select which gpu to use.
Thank you for your answer ;) I think is doing this in the embedded python from ComfyUI ?
Matt
I guess so? I launched CMD in the ..\ComfyUI\venv\Scripts
directory and called the activate.bat
. Then I entered those lines in order.
Oki, thank you very much ;)
What is your cudnn version? onnxruntime-gpu does not support cudnn version 9.x yet. Reducing your cudnn version to 8.9.x may solve your problem.
Hi all,
Thx for your answers, the solution of Bobcate solved my problems and another ;) Thank you again,
Matt
Hi,
I have an error when I try to use "Image Rembg" node : `2024-06-03 12:26:18.3178859 [E:onnxruntime:Default, provider_bridge_ort.cc:1534 onnxruntime::TryGetProviderInfo_TensorRT] D:\a_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1209 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "E:\00_ComfyUI_Fooocus\python_embeded\lib\site-packages\onnxruntime\capi\onnxruntime_providers_tensorrt.dll"
EP Error EP Error D:\a_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:456 onnxruntime::python::RegisterTensorRTPluginsAsCustomOps Please install TensorRT libraries as mentioned in the GPU requirements page, make sure they're in the PATH or LD_LIBRARY_PATH, and that your GPU is supported. when using ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'] Falling back to ['CUDAExecutionProvider', 'CPUExecutionProvider'] and retrying. ****`
I have two graphics cards. One, my primary, is a GTX 1070 Ti for the display and the second one is an RTX 4070 Super for computation (3D, compositing and AI).
What I need to do to avoid this error and use the RTX 4070 Super TensorRT ? Of course, the node switch back to cuda and compute the node.
Thank you,
Matt