I thought this could be a good place for users to post general questions and hopefully get some answers from big brain anons. I'll start. When generating images using wildcards in web-ui, is there a way to determine which option from the wildcard term was selected to generate an image? I feel like being able to know this would be useful for fine-tuning a prompt.

Guides for various generation processes will be primarily documented here. this thread is not for asking questions, please use >>2561 Getting started from scratch on NVIDIA: >>3 (AMD: https://rentry.org/sd-nativeisekaitoo CPU (poorman's): https://rentry.org/cputard | https://rentry.org/webui-cpu) Checkpoint merging and theory: >>4 Typical work flow (gen-upscale-inpaint): >>7 Using textual inversion/LORAs: >>8 Using wildcards: >>1683 Posing subjects with Openpose: >>1685 Advanced prompting tips and tricks: >>2538 Collaborating with others: >>2983 Upscaling beyond 512x512: >>3364

Due to rising interest in all things AI, /bbwai/ has come. This board is just a testbed and threads may eventually be moved back to their respective boards if necessary. Please adhere to these guidelines. These may be updated as we go along. This is a catch-all board. If you are easily triggered, i.e. you stay away from the overboard because you often see things that disturb you, stay clear. Don't like a thread? Hide it. If your preferred genre already has an AI thread on it's board, feel free to continue using it. This board is a place where people interested in all facets of AI can learn from others, regardless of their preferred genre. Even if there is a thread you don't like, you might still learn something from how they are generating the content.

So I'm surprised this hasn't been talked about here yet, as I know there used to be at least one thread in the alt section, I think? Anyway, let's talk about pushing these models to the limit. There are lots of models that are now capable of generating larger body types; but it feels like there hasn't been much progress on generating more unique things. I know HG Swells sorta pioneered the photoshop method of generating an image, coloring it blue in photoshop, and then img2img-ing it, which is how the four sorta realistic ones were generated. However, both of the first two were generated as is without photoshop or anything other than stable diffusion. Of course, generating non-standard body types like blobs or the like is very difficult, as the further you get from the 'norm' the harder it is to tag it and teach it to a model. So post your creations, but also, let's talk about how we got them; if only because it should be fun to see what might be needed to get the models to create things that aren't 'normal.'

A thread for famous fatties.

Post them here! (You can even request them here too.)

Last finally hit limit a few days ago >>23982 >General fat Artist Loras: https://mega.nz/folder/AKoXRZCB#JuOhfrxHsUA6_PeoozproA SyMix IL version: https://mega.nz/file/jvxzyI4L#mFqeJ3YQNfT9EgKhpstVdPF4UJwGvAC19s4YNn9r1ro Guides: >>2 If anyone has an archive of >>2646 feel free to post it.

Post you're favorite current AI wg games and give you're opinions on them.

It's been a while since the last one bump-locked and thread activity died so I suppose I'll take the initiative. You know the drill. Happy Summer """"Updated"""" Archive (10/15/24) https://pastebin.com/ec7gY8AX

last thread got bumplocked, heres a new one. Post your ideal ai generated lolis who are much wider than they’re tall whether it be ones you’ve created or ones you admire. Generations depicting children are not allowed: make sure your posted gens are fictional characters that look distinctly different from actual human children

May as well get this started

a thread for every female character in the Super Smash Bros. series, including assist trophies, Pokéballs and spirits.

Last thread died

The original "Photorealistic cartoon pics" thread was ruined from users getting the wrong impression, so I started a new one. The original thread supposed to focus on AI-generated realistic-styled screenshots from animated shows.

I've been messing with Runway Gen 2 image-to-video and I really like what it does. I'll be making more stuff like this and posting to tumblr https://www.tumblr.com/blog/aibbwvideos anyone know of other people doing similar stuff?