stable-diffusion-webui-model-toolkit VS safetensors

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.

The ML field is doing work in that area: https://github.com/huggingface/safetensors

FYI the file format, safetensors, was proposed, developed and maintained by HF, and involved people from groups such as Eleuther and Stability for external security audits.

https://github.com/huggingface/safetensors https://huggingface.co/blog/safetensors-security-audit

Thank you for note on this. I had not heard there were already trojan horse malware being slipped into tensor files as python scripts. Apparently torch pickle uses eval on the tensor file with no filter.

Heard surprisingly little commentary on this topic. The full explanation of how Safetensors are "Safe" can be found from the developer at: https://github.com/huggingface/safetensors/discussions/111

Here the developer goes into some detail about what kinds of protections .safetensor files have : https://github.com/huggingface/safetensors/discussions/111

Use the safetensors format, which allows safe persistence and loading of models for common libraries - TensorFlow, PyTorch, JAX, etc. We went through external audits in the last few months (blog post). The current direction will be to have this as the default format.

I've been diving in lately and while it's not efficient, the only way to do manage is to create a new conda/mamba environment, or a custom Docker image for all the conflicting packages.

For safety and speed, you should prefer the safetensor format: https://huggingface.co/docs/safetensors/speed

If you know what you are doing you can do your own conversions: https://github.com/huggingface/safetensors or for safety, https://huggingface.co/spaces/diffusers/convert

GitHub - huggingface/safetensors: Simple, safe way to store and distribute tensors