RTX 50 series issues

[MadMan2k]

First, confirm

• I have read the instruction carefully
• I have searched the existing issues
• I have updated the extension to the latest version

What happened?

It seems there are some issues with making it work on the RTX 50 series. I am using AUTOMATIC1111 with CUDA 12.8, along with updated PyTorch (2.6.0+cu128) and Torchvision (0.20.0a0+cu128). The --xformers option is not enabled because it is currently incompatible xformers 0.0.29.post2 now works with RTX 50 series. However, I am still unable to get ReActor to work

Steps to reproduce the problem

Use ReActor with RTX 50 series

Sysinfo

Windows 10, RTX 5070ti

Relevant console log

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.10.1
Commit hash: 82a973c04367123ae98bd9abdf80d9eda9b910e2
Installing requirements
CUDA 12.8
Launching Web UI with arguments:
C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\system\python\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)
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
13:51:28 - ReActor - STATUS - Running v0.7.1-b2 on Device: CUDA
Loading weights [6ce0161689] from C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
Creating model from config: C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\configs\v1-inference.yaml
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 9.4s (prepare environment: 3.9s, import torch: 2.8s, import gradio: 0.6s, setup paths: 0.6s, initialize shared: 0.2s, other imports: 0.3s, load scripts: 0.5s, create ui: 0.3s, gradio launch: 0.2s).
Applying attention optimization: Doggettx... done.
Model loaded in 1.7s (create model: 0.4s, apply weights to model: 1.0s, calculate empty prompt: 0.1s).
13:52:03 - ReActor - STATUS - Working: source face index [0], target face index [0]
13:52:03 - ReActor - STATUS - Analyzing Source Image...
2025-03-29 13:52:03.2913621 [E:onnxruntime:Default, provider_bridge_ort.cc:1548 onnxruntime::TryGetProviderInfo_CUDA] 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 "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\system\python\lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

*************** EP Error ***************
EP Error D:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:857 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasnt able to be loaded. Please install the correct version of CUDA andcuDNN 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.
 when using ['CUDAExecutionProvider']
Falling back to ['CUDAExecutionProvider', 'CPUExecutionProvider'] and retrying.
****************************************
2025-03-29 13:52:03.3504827 [E:onnxruntime:Default, provider_bridge_ort.cc:1548 onnxruntime::TryGetProviderInfo_CUDA] 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 "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\system\python\lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

*** Error completing request
*** Arguments: ('task(o9s8hnfxky4tlgg)', 0.0, <PIL.Image.Image image mode=RGBA size=827x1000 at 0x2C1E43F9810>, None, '', '', True, True, 0.0, 4, 0.0, 512, 512, True, 'None', 'None', 0, False, 1, False, 1, 0, False, 0.5, 0.2, False, 0.9, 0.15, 0.5, False, False, 384, 768, 4096, 409600, 'Maximize area', 0.1, False, ['Horizontal'], False, ['Deepbooru'], <PIL.Image.Image image mode=RGB size=220x220 at 0x2C1E43F98D0>, True, '0', '0', 'inswapper_128.onnx', 'CodeFormer', 1, True, 'None', 1, 1, 1, 0, 0, 0.5, 'CUDA', False, 0, 'None', '', None, False, False, 0.5, 0, 'tab_single') {}
    Traceback (most recent call last):
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\system\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 419, in __init__
        self._create_inference_session(providers, provider_options, disabled_optimizers)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\system\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 483, in _create_inference_session
        sess.initialize_session(providers, provider_options, disabled_optimizers)
    RuntimeError: D:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:857 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasnt able to be loaded. Please install the correct version of CUDA andcuDNN 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.


    The above exception was the direct cause of the following exception:

    Traceback (most recent call last):
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\modules\call_queue.py", line 74, in f
        res = list(func(*args, **kwargs))
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\modules\call_queue.py", line 53, in f
        res = func(*args, **kwargs)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\modules\call_queue.py", line 37, in f
        res = func(*args, **kwargs)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\modules\postprocessing.py", line 133, in run_postprocessing_webui
        return run_postprocessing(*args, **kwargs)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\modules\postprocessing.py", line 73, in run_postprocessing
        scripts.scripts_postproc.run(initial_pp, args)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\modules\scripts_postprocessing.py", line 198, in run
        script.process(single_image, **process_args)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\extensions\sd-webui-reactor\scripts\reactor_faceswap.py", line 688, in process
        result, output, swapped = swap_face(
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\extensions\sd-webui-reactor\scripts\reactor_swapper.py", line 544, in swap_face
        source_faces = analyze_faces(source_img, det_thresh=detection_options.det_thresh, det_maxnum=detection_options.det_maxnum)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\extensions\sd-webui-reactor\scripts\reactor_swapper.py", line 302, in analyze_faces
        face_analyser = copy.deepcopy(getAnalysisModel())
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\extensions\sd-webui-reactor\scripts\reactor_swapper.py", line 145, in getAnalysisModel
        ANALYSIS_MODEL = insightface.app.FaceAnalysis(
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\extensions\sd-webui-reactor\scripts\console_log_patch.py", line 48, in patched_faceanalysis_init
        model = model_zoo.get_model(onnx_file, **kwargs)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\system\python\lib\site-packages\insightface\model_zoo\model_zoo.py", line 96, in get_model
        model = router.get_model(providers=providers, provider_options=provider_options)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\webui\extensions\sd-webui-reactor\scripts\console_log_patch.py", line 21, in patched_get_model
        session = PickableInferenceSession(self.onnx_file, **kwargs)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\system\python\lib\site-packages\insightface\model_zoo\model_zoo.py", line 25, in __init__
        super().__init__(model_path, **kwargs)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\system\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 432, in __init__
        raise fallback_error from e
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\system\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 427, in __init__
        self._create_inference_session(self._fallback_providers, None)
      File "C:\AI\SD_RTX_50\sd.webui-1.10.1-blackwell\system\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 483, in _create_inference_session
        sess.initialize_session(providers, provider_options, disabled_optimizers)
    RuntimeError: D:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:857 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasnt able to be loaded. Please install the correct version of CUDA andcuDNN 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.

Additional information

No response

[Smackdab69]

I'm getting the same issues as well.

[ChenWeiYuan123]

Replace ort = "onnxruntime-gpu==1.17.1" with ort = "onnxruntime-gpu==1.21.1" in the install.py file.
This can run on my RTX 5090.