stablediffusion-directml VS stable-diffusion-webui

stable-diffusion-stability-ai (Directml version)

https://github.com/lshqqytiger/k-diffusion-directml/tree/master --->this will need to be named k-diffusion https://github.com/lshqqytiger/stablediffusion-directml/tree/main ----> this will need to be renamed stable-diffusion-stability-ai

I'm using the directml fork of the Automatic1111 web gui on my AMD RX 6800 XT , and it seems to work fine with txt2img, but my attempts at inpainting to fix up the faces is getting me nowhere. This isn't the browser issue, in that the faces are being shown as being edited in the preview, but they successively converge on the original bad image that's masked... I've attached a youtube clip of how it goes for me. Help!

Download k-diffusion and stablediffusion folders. (click green button "Code" and download as ZIP). Go to the folder you installed in step 1 and browse to repositories, extract these two folders there. Rename them to k-diffusion and stable-diffusion-stability-ai. If you already have these folders delete them first.

There is couple options, easy one for windows is this fork https://github.com/lshqqytiger/stablediffusion-directml you don't need to convert models to onyxxx is simply a1111 using directml so you can use all features like controlnet, but will be probably slower than shark or linux a1111 with rocm (why the hell is there no rocm for windows :/), tbh If I were you, I'd probably try to sell the card and buy, for example, a 3060 12GB

3) install k-diffusion-directml and stablediffusion-directm under ..\stable-diffusion-webui-arc-directml-master\repositories (tutorial)

* LLaVA model: I'll add more documentation. You are right Llava could not generate images. For image generation I don't have immediate plans, but checkout these projects for local image generation.

- https://diffusionbee.com/

- https://github.com/comfyanonymous/ComfyUI

- https://github.com/AUTOMATIC1111/stable-diffusion-webui

I would love to be able to have a native stable diffusion experience, my rx 580 takes 30s to generate a single image. But it does work after following https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki...

I got this up and running on my windows machine in short order and I don't even know what stable diffusion is.

But again, it would be nice to have first class support to locally participate in the fun.

In Auto1111, that just uses Image.blend. :)

https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob...

I used SDXL in automatic1111 webui for both images. Now that I think about it, the procedure I described was how I made this one, but the one that looks like an illustration was done in two steps. I used the canny ControlNet as I said for the outer part of the logo to preserve the shape of the fonts, but I had to turn it off for the boot to give SDXL leeway to add detail and make it look more like a boot.

That said, please do learn coding and don't get discouraged when somebody says to learn PyTorch or recommends using a Jupiter notebook with no further information on how to translate the skill into images. I would highly recommend some short term goals. Get your feet wet by taking apart the UIs. The comfy API documentation is here and the A1111 API documentation is here. There is a difference in completeness, welcome to programming. Writing nodes or plugins is also a good way to jump into this world. Custom wildcard logic might be very attractive to you if you aren't the type that want to deal with a nested file structure to simulate logic.

Possibly Unprompted? https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/8094

version: v1.6.1  •  python: 3.10.13  •  torch: 2.0.1+cu118  •  xformers: 0.0.20  •  gradio: 3.41.2  •  checkpoint: 6e8d4871f8