stable-diffusion-rocm-docker VS stable-diffusion

Let me check my Portainer. Here is a pretty out-of-the-box ready to run container that provides a web interface:

https://github.com/l1na-forever/stable-diffusion-rocm-docker

You may have to do a few slight things to give the docker container access to your GPU. On Fedora Linux I have these packages installed related to ROCm:

    $ dnf list --installed | grep -i rocm

I've had a lot of luck with this in a docker installation Stable Diffusion RoCM Docker but I'm not really good enough with Docker to change things around inside the container. I've also hit a wall a few times trying to get this on linux native, ubuntu 22.04 and 20.04 as well. Currently having kernel version mismatch issues in 20.04 getting the automatic1111 installation to play nice with rocm.

Same, also on an AMD card (I'm on a 6900XT) going through ROCM (the docker image from https://github.com/l1na-forever/stable-diffusion-rocm-docker ) .

use or update this one : https://github.com/hlky/stable-diffusion it has all the samplers, and if you want perfect faces, try k_euler_a

try this one https://github.com/hlky/stable-diffusion you need at least a 1050 to run it tho

https://github.com/hlky/stable-diffusion/issues/153 With 36 comments and tons of before and after comparisons, which are now deleted

I wanted to try hlky version (https://github.com/hlky/stable-diffusion) , due to the WebUI and integration with upscaling models. It should also have the option to be optimized for low VRAM. To avoid getting a green square I have to add the parameters "--precision full --no-half". When I run a prompt, even with the smallest image size, I immediately get a CUDA memory error. Interestingly, without these parameters there isn't any memory error (but, of course, the result is a green square)

Made using https://github.com/hlky/stable-diffusion

Any chance to get this integrated into something like hlky's web ui?

Linux Guide her. Jeg har også Linux, men jeg valgte å sette det opp på Windows boksen min fordi driverne til Nvidia kortet på Linux ikke er helt sammarbeidsvillig når det kommer til å justere viftene etter sensorene i kortet (så jeg må sette det manuelt).

I'm seeing GFPGAN essentially remove all texture from faces, and I only want to use it on the eyes. Any thoughts on how to do this? I am using hlky/stable-diffusion now but I have no issues running a different repo/fork if needed and using command line.