Raul Ciotescu

@bhosalems do you have a link to the paper? is it this one: https://openreview.net/forum?id=u1cQYxRI1H ?

hi @kabachuha just a fyi: the sigma and alpha models have scripts for HF Lora training. https://github.com/PixArt-alpha/PixArt-sigma/blob/master/train_scripts/train_pixart_lora_hf.py https://github.com/PixArt-alpha/PixArt-alpha/blob/master/train_scripts/train_pixart_lora_hf.py there are also PRs for text-encoder training in parallel. if you want...

@kabachuha yes, please add me i will start next week. do you also have an overview of what has been done so far and what needs to be done?

@kabachuha so the still open todos are following. looks like mostly testing? - Combine T5 and SDXL vae in checkpoint when saving, recommended by [FurkanGozukara](https://github.com/FurkanGozukara) - Do test launch on...

@yiyixuxu that is the pixart controlnet model for HED conditioning as uploaded by the authors of pixart. for this pipeline i have converted the controlnet layers to safetensors, uploaded here...

@asomoza > why does it have its own implementation of the HED detector? It doesn't work with the regular one that everyone uses? Have you tested it with the one...

> thanks, I'll give it a test later. I was asking because if it was trained with a custom HED detector which produces different results than the default one it...

i have to correct my previous comment. i was using the default params for HED, which converted the image to 512, if i use however 1024 it works as it...

@asomoza > Thanks, the results looks nice, since we only have one controlnet, maybe do what @yiyixuxu suggested, lets start with a community pipeline first and then as it gets...

@yiyixuxu @asomoza have moved all to the examples folder i have also added the training script. together with sh files for starting the training and for running the pipeline