sd-extension-system-info VS voltaML-fast-stable-diffusion

I've been using both SD and various LLM on linux without any issue and have done so for months. Windows support is also starting to roll out slowly, with koboldcpp-rocm recently giving me 20-25+t/s for a13B even on windows. you can see what SD performance is like on sites like these. those numbers roughly match what i get on my RX6800 as well (8t/s).

That seems a lot worse than a 2060 SUPER with PyTorch in A1111.

https://vladmandic.github.io/sd-extension-system-info/pages/... (search for 2060 SUPER)

But usually A1111 users use benchmark on this extension https://github.com/vladmandic/sd-extension-system-info

AMD SD = Setup Diaster? it was quite troublesome googling the few linux/amdgpu/rocm/sd vers/configs/params posts online. Also the whole PC may hang during generation which is bad for the harddisk. Your card is way more powerful so may not hang like mine. People are getting 8it/s https://vladmandic.github.io/sd-extension-system-info/pages/benchmark.html

According to system info benchmark, M40 is like 1-2 it/s and P4 is barely better than that.

Anyway to properly "benchmark" the impacts different switches on your image generation speed, it is better to use the benchmarking utility from extension https://github.com/vladmandic/sd-extension-system-info (it also creates a very handy table of results from other users at https://vladmandic.github.io/sd-extension-system-info/pages/benchmark.html for you to compare with.

I can see that the top performance benchmark results on SD WebUI Benchmark Data (using RTX 4090), are obtained through WSL2 running Automatic1111 on a Linux dist and Python 3.10.11, along with PyTorch 2.1.0.dev+cu121 (like benchmark id: 4126)

You should be able to compare based on the published benchmarks, just replicate the settings based on what's reported https://vladmandic.github.io/sd-extension-system-info/pages/benchmark.html

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