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.

Last thread died

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?

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

thought we could use a thread for slob bots of all sorts. burping, farting, messy eating etc. all welcome, but maybe tag the fetishes too, especially if the bot has polarizing fetishes like scat or health issues. I'll start off with my own: Xartha, a gluttonous alien queen https://c.ai/c/pfz8IVyVbAOB7fBsifTi1z4nlBgQiraeZ3j9T8DJc-Y features: gradual wg, burping, farting, corruption image is from alt btw

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

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

Grok is awesome now. Here are two comparisons I’ve made so far. One of Sabrina Carpenter, the other of streamer, Sweet Anita. With both comparisons, the first image is the one I inputted and the second is what was generated. I’d love to see some of you guys’ creations!

post girls with huge ass/thighs any size is good, slimthick or ssbbws just make the ass big

Back again with more experimentation. Always loved the Charlie X episode of Star Trek but have long considered his choices of cruel transformations a lost opportunity for *fucking massive weight gain*. But no more! Here are two xxxxxxxxwg variants, one using Grok Imagine and the other using Pixverse. They both have their pros and cons. You've seen the episode and know that Charlie has two victims left that I haven't given the alternative tf treatment to, so if anyone has any suggestions, I'll take them into consideration for a future video. https://fast-file.ru/622bf6f5 https://fast-file.ru/71f30b58

Last one hit post limit and we need more furry degeneracy Previous thread: >>6563

Trying to make a consistent weight gain story using only AI technology and a little bit of editing. More like a proof of concept at this point. The images I used to make the video were really shitty and rushed. But I am planning to improve and continue.

The thirteenth edition of request thread. (Apologies for the fuckup when posted in a previous thread) Request a character with a prompt and an image, and hope someone helps you. Tag the Request Anchor with your requests Tag the Delivery Anchor with your deliveries. >Please be sure there is already a LoRA or Lycoris available for your request on civitai.com: without one, your request is likely to go unfulfilled. Previous thread (>>31996)