Hello, I seem to have encountered some problems running the ‘fourpeople_workflow.json’ you reserved.

[Chzzll]

Error occurred when executing YOLOTrackerNode:

Could not run 'torchvision::nms' with arguments from the 'CUDA' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'torchvision::nms' is only available for these backends: [CPU, Meta, QuantizedCPU, BackendSelect, Python, FuncTorchDynamicLayerBackMode, Functionalize, Named, Conjugate, Negative, ZeroTensor, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradMPS, AutogradXPU, AutogradHPU, AutogradLazy, AutogradMeta, Tracer, AutocastCPU, AutocastCUDA, FuncTorchBatched, BatchedNestedTensor, FuncTorchVmapMode, Batched, VmapMode, FuncTorchGradWrapper, PythonTLSSnapshot, FuncTorchDynamicLayerFrontMode, PreDispatch, PythonDispatcher].
Is my yolov8m model placed incorrectly? Can you give me the correct model download address? Thank you.

[logtd]

Hey, thanks for the interest!

Unfortunately I don't maintain the tracking nodes any more since they've been replaced by SAM2.

I've been meaning to redo the Instance Diffusion to take SAM2 masks, but SD1.5 interest isn't very high any more.

[ritonV]

Well, it's very sad that you don't support that node, because it's a really great feature that could not be found elsewhere. All AI animations are made for only one character, that is very limited. It would be great to port it for SDXL or Flux, or a video model like LTX !