[Request] ONNX model optimization through GUI for DirectML background (Olive, ONNX runtime, OpenVINO)

It would be nice to have GUI model optimizations same as in StableDifusion webui or Chainner.

There is a lot of documentation and Chainner method seems to be most user friendly for optimizing ONNX models but it doesn't give too much of performance difference on Intel GPU.

Expectations would be to have easy GUI method for optimizing ONNX models on Intel GPU.
Quantitize, Graph optimization model etc.

Nice to have would be comparator of performance difference between not optimized and optimized model. It can be achieved by measuring "Inference Time".