nix-ld VS stable-diffusion-webui

You may be interested in `nix-ld`. https://github.com/Mic92/nix-ld

As I mentioned I used nix-index to build LD_LIBRARY_PATH. I believe I picked that up from nix-ld. The README on that page shows an example and mentions some tools (nix-autobahn, nix-alien, and nix-index) to help figure it out.

Hi guys, I really like NixOS. I also do not want to miss nix-ld, because it allows me to run "normal" Linux programs on nix.

As someone who has been using NixOS for a couple of years now, I really want to say how appreciative I am of everybody for making noticeable improvements to the system on a somewhat regular basis. The nix command keeps on adding great new features like flake templates and bundling as well as just being more user friendly (error messages, actionable hints, etc.) Additionally, tools like nix-ld [1] make nix more usable than ever with software from external sources. Things just keep on getting better for NixOS users!

Despite the reputation, I feel that NixOS or some derivative of it has the power to become the best distribution for non-technical users in the long run. What NixOS has done is effectively built an interface to every component of a modern Linux system, all that needs to be built is a user application to take advantage of it. Of course, there still needs be some improvements in Nix itself for it to blossom into its final form, but I really see a path to greatness here.

I have often thought about creating a simple unified Win2K-esq or BeOS-like X11 WM/DE specifically for NixOS but unfortunately I like the time/motivation.

[1] https://github.com/Mic92/nix-ld

Regarding the ld thing, I don't know if this is relevant but probably: https://github.com/Mic92/nix-ld

Have a look at nix-ld and nix-autobahn.

* 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