stable-diffusion-webui-directml VS automatic

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.

> it won't ever be a viable option

For production workloads, I generally agree. It's an unsupported hack with a questionable future, I wouldn't do anything money-making with it.

However, for tinkering and consumer workloads, it already works pretty well. Enough of cuDNN and cuBLAS work to run PyTorch and in turn, Stable Diffusion with https://github.com/lshqqytiger/ZLUDA - there's even a fairly user-friendly setup process already in https://github.com/vladmandic/automatic .

I was able to get a personal non-ML related project working on my AMD card in just a few minutes, which saved me a lot of development time before I then deployed the production workload on NV hardware (this is probably why AMD pulled the plug on the project - it's almost more of a boost to NV than anything else, AMD really need people to be writing code on ROCm to deploy on AMD datacenter hardware).

While I currently use SD.Next[1], I have tested ComfyUI locally with my AMD card. The UI can be daunting, but you learn quite a great deal about how a Stable Diffusion pipeline works. In addition some innovations and advances find their way into ComfyUI first.

[1] https://github.com/vladmandic/automatic

I used SD.NEXT ( https://github.com/vladmandic/automatic ) and https://civitai.com/models/82098/add-more-details-detail-enhancer-tweaker-lora and epicphotogasm_lastUnicorn

I found this thread on GitHub talking about how this was fixed in the latest version with an optional setting. I tried enabling it, as they mentioned, but it just resulted in an immediate CUDA out of memory error when starting generation. So it seems I'm actually needing the shared memory, which I assume is my issue.

As always, do check out our more detailed changelog, give us a quick install from our Repo, and stop by our Discord Server for any questions or help you may need.

SD.Next

Today I finally wanted to give SDXL a chance, so I set everythin up according to Vladmandic's Wiki https://github.com/vladmandic/automatic/wiki/SD-XL

I'm trying to get SDXL working on Vlad's SDNext, but I keep getting the error in the title when trying to run basic operations. I'm not sure what's going on, I followed his guide for it to a T.

We used an inference container based on SDNext, along with a custom worker written in Typescript that implemented the job processing pipeline. The worker used HTTP to communicate with both the SDNext container and with our batch framework.