stable-diffusion-webui-directml VS sd-extension-system-info

I'm getting this error using (https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues), freshly installed. I'm running it on an AMD RX 6700 XT with 12gb of vram. Generating a single image at default settings (512x512, 20 steps, etc.) I can do simple prompts (i.e. "kitty cat") but as soon as I add a couple more tags, I get the aforementioned error message, usually 20-30% into generating an image. I went through this thread (https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/38) and tried every solution I saw, most of them being variations of adding --medvram --precision full --no-half --no-half-vae --opt-split-attention-v1 --opt-sub-quad-attention --disable-nan-check to the commandline arguments. What else might I be able to try? Thanks.

i use automatic 1111 you can find the installation on the github , this branch https://github.com/lshqqytiger/stable-diffusion-webui-directml and it works fine although the speed is what it is, i also have a old GPU.

I'm using this one: https://github.com/lshqqytiger/stable-diffusion-webui-directml

- https://github.com/lshqqytiger/stable-diffusion-webui-directm - starting webuser-ui with COMMANDLINE_ARGS=--opt-sub-quad-attention –disable-nan-check - AMD 8GB Radeon Pro WX7100

I'm running this fork (https://github.com/lshqqytiger/stable-diffusion-webui-directml) on a pc with a Ryzen 5700x and a Radeon RX 6700 XT 12 GB Video Card.

I am using direct-ml fork

Im running Stable diffusion on my 6900XT, and I feel like its way slower than normal. Using the updated Webui https://github.com/lshqqytiger/stable-diffusion-webui-directml.

This refers to the use of iGPUs (example: Ryzen 5 5600G). No graphic card, only an APU. The DirectML Fork of Stable Diffusion (SD in short from now on) works pretty good with AMD. But not only with the GPUs, but also with only-APUs without GPUs.

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