voltaML-fast-stable-diffusion VS imaginAIry

Also, VoltaML has a good reference GPU AITemplate SD 1.5 implementation:

https://github.com/VoltaML/voltaML-fast-stable-diffusion/tre...

The speed jump is massive on my desktop GPU, probably even more dramatic on cloud hardware, and it may support some things (weight swapping/lora swapping/resolution changing) better than JAX.

This kind of drama is just sad.

I dont know if you are OP, but plenty of other UIs have interrogator code, like https://github.com/VoltaML/voltaML-fast-stable-diffusion/tre...

If you just want an accelerated ui, you can check https://github.com/ddPn08/Lsmith/ or https://github.com/VoltaML/voltaML-fast-stable-diffusion which also use the same origina nvidia code. These projects don't do img2img though, you can check in my repo for the img2img pipeline if you need. You need to compile the tensorrt engines for the models first. There are a few steps you can check in their script: export onnx, optimize onnx, compile engine for optimized onnx. I streamlined that a bit and I normally just run my compile.py in docker to build engines.

Try https://github.com/VoltaML/voltaML-fast-stable-diffusion

This one: VoltaML/voltaML-fast-stable-diffusion: Lightweight library to accelerate Stable-Diffusion, Dreambooth into fastest inference models with single line of code 🔥 🔥 (github.com)

You will be waiting a lot longer for this to be implemented: https://github.com/VoltaML/voltaML-fast-stable-diffusion

Stable Diffusion works fine on a CPU - on an AMD Ryzen 5700, approx 90s per image (and I believe comparable or faster on my old i7-6700). If you want to kick off a batch in the background while you work on something else, that's plenty fast. (I use: https://github.com/brycedrennan/imaginAIry).

Yeah, also, rather than messing around with the AUTO1111 UI, maybe learn some Python and how to use this library: https://github.com/brycedrennan/imaginAIry

this is a real thing https://github.com/brycedrennan/imaginAIry