sd-extension-system-info VS multidiffusion-upscaler-for-automatic1111

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

Use tiled VAE, it will save VRAM: pkuliyi2015/multidiffusion-upscaler-for-automatic1111: Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0 (github.com)

My favorite solution is to not use ultimate Sd upscale and instead use multidiffusion-upscaler.

sure, i personally use 'tiled diffusion' https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111, works like charm also use adetailer for faces if its needed.

What worked for my 1080 was using TiledVAE and turning down the quality of my previews - I don't pay much attention to it/s but it's definitely faster than using --medvram, and now I can handle batches and large resolutions without things exploding on me.

I would highly recommend adding https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 to your A1111 installation, TiledVAE is enabled automatically under the hood in A8R8; this will allow you to get even larger generations before getting an out of memory error. You'll get a Tiled Diffusion checkbox with some reasonable hardcoded defaults as well.

Use Tiled VAE https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111

That's weird. 10GB should allow you to hires to 2048x2048 at least. Use Tiled VAE extension https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 that will allow you to go even beyond that.