Hacker News Reader

Comment by nowandlater | Hacker News Reader

This is the one I've been using https://github.com/sd-webui/stable-diffusion-webui . docker-compose up , works great.

I've also been using this one (wasn't sure at first, they just migrated from the /hlky/ namespace on GitHub), but I have no idea at first glance what the differences are.

I will say that this one has had REALLY active development as new features have been coming out, and is pretty polished at this point (albeit I'm using it more as a toy than anything, but it's awesome to have a quick way to use the new features that have been shipping out).

Seems like it fails if you have an AMD GPU instead of an Nvidia one (at least that's my guess, based on the error contents):

  ERROR: for stable-diffusion  Cannot start service stable-diffusion: failed to create shim: OCI runtime create failed: container_linux.go:380: starting container process caused: process_linux.go:545: container init caused: Running hook #0:: error running hook: exit status 1, stdout: , stderr: nvidia-container-cli: initialization error: load library failed: libnvidia-ml.so.1: cannot open shared object file: no such file or directory: unknown

Indeed, Stable Diffusion does not currently run on AMD graphics cards.

Some people have been able to run on recent AMD cards with rocm: https://github.com/CompVis/stable-diffusion/issues/48

I'm able to run it on my rx6900 xt on Linux.

I tried using a docker container and it took 3 min to generate a prompt. However it seems that 2:45 min is somehow spent on tje GPU and finally the remaining 15 seconds the GPU gets utilized.

I haven't had the time to look into this yet, but it does seem to work.

It does, on Linux, Windows, and MacOS.

I've gotten it running with a Radeon RX 6800 on Ubuntu Linux 22.04 (with overwriting PyTorch with a ROCm-supporting version), and on Windows 10 (in a very barebones way using ONNX), but are there better, more full-featured ways to get it running on Windows? Would love to know.

Is there a way to run this in the cloud? On Google Colab or elsewhere?

Colab: https://colab.research.google.com/github/WASasquatch/StableD...

To run it elsewhere in the cloud, grab a GPU (spot) instance and SSH in.

You mean a VM on a machine with a GPU? Or does it have to be a bare metal machine? What is a good provider of suitable VMs/machines?

And what do you do after you SSHed in? The installation instructions seem to be for windows users (click here, then click there ...) is there a linux script that does the installation automatically?

Just a VM with a GPU, doesn't need to be bare metal. AWS/GCP/Azure has em, but for GPU cloud instances, boutique vendors like CoreWeave, runpod, lambdalabs.com, vast.ai, paperspace may be more competitive.

Parent comment alludes to docker-compose up.

You can run docker inside a VM? And it will be able to use the GPU and tunnel port 80 through the docker container, through the VM and to the web?

There's some trickery and details, but yes: https://github.com/NVIDIA/nvidia-docker

You can also get windows instances with GPU attached and RDP in, though personally I prefer Linux

https://docs.aws.amazon.com/AWSEC2/latest/WindowsGuide/accel...

Here's an install script if you need handholding :) https://github.com/JoshuaKimsey/Linux-StableDiffusion-Script...

Lambda Labs is probably cheaper: https://lambdalabs.com/service/gpu-cloud

I like this one but had some trouble with using img2img. Maybe my image was too small (it was smaller than 512x512). Failed with the same signature as an issue that was closed with a fix.

I am mobile, but there's an issue reported on github about img2img

Reply on news.ycombinator.com