stable-diffusion-webui-model-toolkit VS SDAtom-WebUi-client-queue-ext

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.

Using a Queue Extension. I use SDAtom-WebUi-client-queue-ext to queue my jobs. Before I sleep, I just click "GO" and later I will have pictures with very different prompts, it even switches checkpoints for you if needed. https://github.com/Kryptortio/SDAtom-WebUi-client-queue-ext