lllyasviel / lllyasviel/stable-diffusion-webui-forge
onnixruntime throwing new error
- Dominant language
- Python
- Stars
- 13k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
This only happens when I use 'Remove Background' in the 'Extras'.
It doesn't seem to affect the output, still does a good job of removing backgrounds, making them transparent, typically in batch mode.
I've noticed the directory the error references is: D:\a\_work\1\s\onnxruntime\python\, which doesn't exist, so it may be a temp dir that's created at runtime, but that's just a guess.
I seem to have all the stuff it's complaining about not finding and haven't seen this error before in the two years or more I've run Forge. Anybody know what's up with this?
Did something update behind my back and cause Forge to throw this error?
My Installed Setup:
CUDA 13.1
MSVC runtime v14 (2017-2022)
D:\Forge\system\python\lib\site-packages\onnxruntime\capi\onnixruntime_providers_cuda.dll
D:\Forge\system\python\lib\site-packages\onnxruntime\capi\onnixruntime_providers_tensorrt.dll
*************** EP Error ***************
EP Error D:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:490 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.
****************************************
2026-07-26 11:38:53.0753179 [E:onnxruntime:Default, provider_bridge_ort.cc:1992 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1637 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "D:\Forge\system\python\lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"
2026-07-26 11:38:53.0895075 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:965 onnxruntime::python::CreateExecutionProviderInstance] Failed to create CUDAExecutionProvider. Require cuDNN 9.* and CUDA 12.*, and the latest MSVC runtime. Please install all dependencies as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing Remove Background from Extras in batch mode and inspect the onnxruntime provider-loading messages for the CUDA and TensorRT execution providers. Compare the installed onnxruntime DLLs and CUDA, cuDNN, and MSVC versions with the linked ONNX Runtime GPU requirements. Done means identifying the missing or incompatible dependency and documenting or fixing the supported setup.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100