Mike Howles

> > Turns out the background layers take up alot of memory and shaving that down allowed me to train a model on limited memory. Can you share where you...

Agreed! It would be nice to have similar metadata such as what koyha_ss bakes in.

> There already is an option to save the entire training configuration in the safetensors file. The only thing not included are the captions and trigger words, because those don't...

> > The data loader is not set up to provide that kind of information > > actually that's what I miss - after if you train 10+ loras you...

Hey, I'm glad you've been able to hopefully use it for some things! Regarding Window Coverings, I never finished that one as I do not have any devices to know...

Hey guys - Sorry for the lack of response from me. This ended up being a "one and done" thing for me and I never used it again. Please feel...

I changed the last line of `flux_train_ui.py` to: ```py demo.launch(share=False, show_error=True, server_name="0.0.0.0") ```