im having this error on macOS m2 MacBook Pro,

[hopye]

Yesterday it was working fine, but can't seem to figure why this is happening, simple node setup, to load images, reactor and preview. comfyui,

have tried different source and input images

[ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running CoreML_5101909898278375113_6 node. Name:'CoreMLExecutionProvider_CoreML_5101909898278375113_6_6' Status Message: Exception: /Users/runner/work/1/s/onnxruntime/core/providers/coreml/model/model.mm:66 InlinedVector<int64_t> onnxruntime::coreml::(anonymous namespace)::GetStaticOutputShape(gsl::span, gsl::span, const logging::Logger &) inferred_shape.size() == coreml_static_shape.size() was false. CoreML static output shape ({1,1,1,800,1}) and inferred shape ({3200,1}) have different ranks.

[chinesewebman]

I met with the same error, after removed several loras, it works again.

[leiy88]

My Solution:
modify comfyui-reactor/scripts/reactor_swapper.py switch from using the CoreMLExecutionProvider (for Apple Silicon MPS) to the CPUExecutionProvider.
Before:

 33 # PROVIDERS
 34 try:
 35     if torch.cuda.is_available():
 36     ┆   providers = ["CUDAExecutionProvider"]
 37     elif torch.backends.mps.is_available():
 38     ┆   providers = ["CoreMLExecutionProvider"]
 39     elif hasattr(torch,'dml') or hasattr(torch,'privateuseone'):
 40     ┆   providers = ["ROCMExecutionProvider"]
 41     else:
 42     ┆   providers = ["CPUExecutionProvider"]
 43 except Exception as e:
 44     logger.debug(f"ExecutionProviderError: {e}.\nEP is set to CPU.")
 45     providers = ["CPUExecutionProvider"]

After

providers = ["CPUExecutionProvider"]

I dont know why mps causing this issue, but this method sloved it anyway.