DeepDanbooru VS stable-diffusion-webui

Okay, it turns out that someone has trained an image classifier on danbooru as a dataset.

First of all - DeepDanbooru is the exclusive project of KichangKim, who aimed to train models based on (variants of) the ResNet architecture to output Danbooru tags.

> pip install -r requirements.txt Like what does this mean, where do i put the files i got from https://github.com/KichangKim/DeepDanbooru ? The whole process is confusing me

For: https://github.com/KichangKim/DeepDanbooru I see the "Put your deepbooru release project folder here.txt" file so I "git clone" it into this folder, moved it up and so on but the button did not show and in the console are no errors. Also I restarted the UI after each moving of the project.

if not is_installed("deepdanbooru") and deepdanbooru: run_pip("install git+https://github.com/KichangKim/DeepDanbooru.git@edf73df4cdaeea2cf00e9ac08bd8a9026b7a7b26#egg=deepdanbooru[tensorflow] tensorflow==2.10.0 tensorflow-io==0.27.0", "deepdanbooru")

i think you could make an argument that training an art-generator model falls afoul of the "market for the original work" prong of fair use in a pretty severe way. but something like DeepDanbooru where the output is not the image but a descriptor of it would be a much easier sell as fair use.

DeepDanbooru is suprisingly good for tagging photos and drawings.

* 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