auto-sd-paint-ext VS OnnxDiffusersUI

It makes more sense to embed stable diffusion capabilities into well-established image editors such as Gimp, Photoshop, Krita, or Figma, which come with layered, non-destructive functionalities, rather than attempting the opposite approach.

https://github.com/Interpause/auto-sd-paint-ext

You might be interested in knowing that Krita has a SD plug in that I've found works quite well if you're willing and able to install and run SD locally. Krita is now my primary art program. https://github.com/Interpause/auto-sd-paint-ext

GitHub - Interpause/auto-sd-paint-ext: Extension for AUTOMATIC1111 to add custom backend API for Krita Plugin & more

Yep, Krita has a SD plugin too ( https://github.com/Interpause/auto-sd-paint-ext ) but probably not as good as this Photoshop one yet.

Again in my humble opinion, however, it's nice to be able to choose (at least if you're willing to pay the subscription costs) among different models and algorithms. Use whatever suits best your needs or your ideas. I personally prefer SD's versatility, and the workflows enabled by "being able to get my hands on all the parameters", like sampler selection, CFG scale, inpainting and other stuff (have you tried InvokeAI's unified canvas or Automatic1111's Krita plugin?). Not to mention the ability to do progressive and potentially infinite upscaling of an image (Automatic1111's "SD upscale" script or InvokeAI's "Embiggen").

I have a simple question that apparently i cant seem to figure out for the past like 12 hours, im using the https://github.com/Interpause/auto-sd-paint-ext auto extension for the krita plugin, and im simply just trying to inpaint creatures and just general things into a scene, but no matter what i do, the result is nothing like it, i followed the inpainting tutorial they have listed on github (New layer from visible) then make a new layer to paint the mask on, tried all fill methods with different steps, im fairly new to all of this and what not, im using a custom model checkpoint btw if that matters (protogen 5.8)

Sounds like Automatic1111 doesn't work with your AMD RX570 so it uses your CPU instead. There's a guy that tried a few workarounds on his github page that might help but you basically need to buy a GPU made in the last 3 years that has ray tracing capability. https://github.com/azuritecoin/OnnxDiffusersUI

Onnx Diffusers UI

Its this one: https://github.com/azuritecoin/OnnxDiffusersUI It works properly except i can't convert models other than the default it comes with.

https://github.com/azuritecoin/OnnxDiffusersUI this seems to work pretty good for me, has quite a bit of features and has a CPU only mode, only problem with it is, it hogs a lot of ram

for windows the onnx ui:https://github.com/azuritecoin/OnnxDiffusersUI, or you can try and fenagle your way into installing automatic1111 on linux

Guide

I also have a 6800 and when I'm on Windows I mess around with this https://github.com/azuritecoin/OnnxDiffusersUI which is fine and works okay but yeah without ROCm it is very slow. I usually just dualboot into Linux if I want to spend more time generating things. It's just how it is for now with support for AMD, sadly.