Danylo

I solved the problem by implementing a longPressGestureRecognizer and doing smth like this in gesture.state == .began / .changed: ``` let gestureLocation = gesture.location(in: chart) guard let highlight = chart.getHighlightByTouchPoint(gestureLocation)...

Hey @jrittvo thanks so much for the link! Didn't know we could do that with LoRAs, gonna test a couple of your models now

Hi again @jrittvo The models work great, thanks again for this insight. Would you mind sharing some info on how you converted the output `.safetensors` model (from the SuperMerger extension)...

@GuiyeC that's awesome, thanks! At the moment I stopped experimenting with LoRAs, as it's crucial for us to "hot-swap" them. E.g., have one SD model (~1Gb), and multiple LoRA models...

This [commit](https://github.com/apple/ml-stable-diffusion/commit/b8b5e886df33f610c6986494f31b0206a55dc8d8) needs to be reverted/fixed. Using multiple controlNets is impossible at the moment

Hi @atiorh sorry for the delay I'm seeing a similar error when using the CLI: ``` Build complete! (0.16s) Loading resources and creating pipeline (Note: This can take a while...

Hi @atiorh I'm still running into the same crash on latest main

@Thons thanks! I actually tried the solution you sent and ran into the same accelerate crash. Will try the fix tomorrow!

@atiorh the fix provided by @Thons works, I'm able to generate images using multiple ControlNet models, but this brings me to this https://github.com/apple/ml-stable-diffusion/issues/216 issue - only the first ControlNet model...

I tried bringing back the old CN logic (slow, but supports multiple CN models) while working around the MLShapedArray crash like so, and generating an image with inpaint + canny...