Import or Use ONNX in comfyui

### Your question

Hey guys, these past few months I've noticed Nvidia has dropped several models in ONNX format. But honestly, I have no clue how to use them within ComfyUI. I get there are some TensorRT nodes, but those manually convert the model to their own extension (.engine), while other webUIs like Automatic1111 have ONNX integration built-in.

Could someone explain or make a tutorial on how I can use these ONNX models in ComfyUI?

I have an RTX 4000 series card. Thanks a bunch!

For example, I'd love to use this fp8 ONNX >> https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev-onnx/

Or https://huggingface.co/stabilityai/stable-diffusion-3-medium-tensorrt

Is possible use it in comfyui?