Astroboy

Same situation here. Almost all my upscaled images with LDSR have these black areas on the bottom side.

@Phhofm great guide! Thank you so much for the detailed explanation. So, the magic pixel size is 128. It will be two times more job time if I want to...

> can't make it run on windows natively, getting this error after running **python train_dreambooth.py** > > train_dreambooth.py: error: the following arguments are required: --pretrained_m odel_name_or_path, --pretrained_vae_name_or_path, --instance_data_dir > >...

@patrickgalbraith , thanks for sharing this clean code. I wonder why you are using the LR Scheduler with the "polynomial". Did you get better results compared with "constant" parameter? I...

@InB4DevOps > Thank you so much. This will save so much time :)

Try to use the below link. The model link that you're trying to train is not suitable for training. https://huggingface.co/geocine/protogen-diffusers

> @chris-aeviator Hey, I wonder if those YAML files do the work in your case? Or is there any other YAML file sources that you are using with your fine-tuned...

> I have success with 2.1 768, but always have unusable result with 2.1 512(base) model Thanks for the feedback! I wonder if there is an update on the repo,...

I have the same problem. When I used the verbose command it has showed me this error: `python: can't open file 'I:\\AI\\oobabooga\\setup_cuda.py': [Errno 2] No such file or directory`

> > I have the same problem. When I used the verbose command it has showed me this error: `python: can't open file 'I:\\AI\\oobabooga\\setup_cuda.py': [Errno 2] No such file or...