seait VS stable-diffusion-webui-model-toolkit

install the recommended python and git from windows store and try from here to install automatic1111 from here https://github.com/diStyApps/seait its a gui and very simple just one click do install it will create a new separate venv just make sure your python is version is updated

Initial release will be public. and for easier installation it also be available trough https://github.com/diStyApps/seait

use https://github.com/diStyApps/seait/releases/download/0.1.4/seait_installers_version_0.1.4.zip

If you are on windows, you could just do a second install with SEAiT.

Try this...https://github.com/diStyApps/seait

seait is a life saver now

maybe try seait? https://github.com/diStyApps/seait is like for people who don't really know deep about installing stable diffusion, here is the video about it https://www.youtube.com/watch?v=_PJe_gSZn7I

there is an extension for auto1111 that can clean up models. GitHub - arenasys/stable-diffusion-webui-model-toolkit: A Multipurpose toolkit for managing, editing and creating models.

It's in the available extensions list or here: https://github.com/arenasys/stable-diffusion-webui-model-toolkit

Have you tried using the https://github.com/arenasys/stable-diffusion-webui-model-toolkit extension to prune the mega mix and see what the difference is?

Pytorch2.0 seems to use a bunch more memory on my end, though more testing is necessary to confirm that. This would limit your image size. But, you can reclaim some of that back if you run your models through the model toolkit. It's an extension that cuts out unneeded data from your model files, which will save space in your VRAM. Cut realisticVision almost in half (3.7GB > 2.0GB). | You can also run a lower batch size but a higher batch count.

You might be able to use the model toolkit to remove extra bloat from models to get it under that VRAM requirement.