automatic VS stable-diffusion-ui

> 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.

CMDR2's 1-Click Installer

Hey so i'm currently using easydiffusion but its missing one feature i've been really wanting to play around with recently. Video, and i've heard from some others that its one of the easiest to install but least peformant and worse options you can get; so what do you guys suggest?

Or just use the CPU and it works, just takes a few minutes. stable diffusion cpu But don't let me stop you, I need one too.

No. CUDA is very straightforward. There is even a nice project that sets up Stable Diffusion for you. With basically no knowledge about AI i was able to get it to run. If i recall correctly i just needed to install one dependency manually, and i was provided with nice web gui for playing with it.

You could read the guide first: https://github.com/cmdr2/stable-diffusion-ui/wiki/UI-Overview or Start easy diffusion

Thanks and your right there are loads, trying out this from GitHub

Simplest start https://github.com/cmdr2/stable-diffusion-ui

First is Easy Diffusion, you need to be online just once to run the installer. It downloads several extra files. Let it finish and then make some test pictures. Exit everything (browser window and text window). Then anytime you want to run it, just turn off internet and run the batch file to start it up. No internet!

Yesterday I got Easy Diffusion to work (on Windows only), but it refuses to use the GPU and instead uses the CPU, which of course, takes nearly an hour to make a 512x512 image.