sd-extension-system-info VS scribble-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

Text to image with Scribble Diffusion

Eh, I don't think this is better than https://scribblediffusion.com/. None of the three images were at all like my drawing, but Scribble Diffusion did include the right elements in the right places.

Demo: Scribble Diffusion GitHub: Scribble Diffusion Repository

You can get several free acccess interactions with a version here ControlNet Scribble (ie if you keep using it for long enough/ several tries then it will ask you to set up an account) ...... this is the backend for a simpler browser interface at Scribble Diffusion but the ControlNet one above allows you to upload an image, so, yeah draw a scribble on a piece of paper, take a photo with your phone and then upload

I feel embarrassed to jump on the AI bandwagon, but have you tried uploading this into something like Scribble Diffusion?

ScribbleDiffusion: Turns scribbles with descriptions into really cool images.

scribblediffusion.com

Thanks so much! You should try it! In this case my drawing is more elaborate, but you will be surprised that the simplest drawing can achieve great results! If your drawing is not very good then the prompt is very important! Give it a try at https://scribblediffusion.com/ and let me know how it went!