martintomov
martintomov
Thanks for the quick reply! Yeah, I suspect Comfy can't really solve this, but I wonder what's the current workaround for the issue I'm facing and if others are also...
### @sagebru5h Try using this: https://github.com/MarkoCa1/ComfyUI_Segment_Mask/issues/5
I'm looking forward for mac arm support too
You maybe missed to run `git submodule update --init --recursive`.
You can upload it as a model to hugging face and use the Inference API, if that works for you. This way you can use diffusers pipeline also
use this script to make your LoRA compatible with comfy (and everything else): https://huggingface.co/comfyanonymous/flux_RealismLora_converted_comfyui/blob/main/convert.py
it surely could work, check https://x.com/jfischoff/status/1824183079549931736 by fal.ai their flux trainer is using ai-toolkit, but i'm not sure what they use to merge loras yet
Replace from ```pkg_resources import packaging``` to ```import packaging``` ## https://github.com/pytorch/serve/issues/3176
try this: > Hi, turns out the issue was that I was using the wrong start command (on Windows) so use **python run.py config/whatever_you_want.yml** instead of **python3 run.py config/whatever_you_want.yml** This...
what do you mean by upload images? you just need to put them in a folder and specify a path. Windows: ```"C:\\path\\to\\images\\folder"``` Linux: ```"C:\path\to\images\folder"```