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

https://stuffer.ai Been giving this a shot both a few weeks ago and over the past couple of days, and it's gotten much better at producing AI fats than it used to be. Still outclassed by custom colab/local SD models using the newest BiggerGirls models, but for a free web implementation without registration and with a fast image gen pace, it's pretty decent. As a bonus, you don't have to spend eons dancing around arbitrary word filters like you do with the censorship hell bing's dall-e implementation has sunken into. To start us off, here's some good results I got with various permutations of these two prompts: >bottom-heavy SSBBW trapped in a narrow doorway, huge ass, huge hips, huge thighs, pear-shaped, sweaty, aroused, irritated >sketch, princess daisy [insert scene/action here], huge belly, bloated belly, swollen belly, sweaty, aroused, blushing, belly noises

Ladies & Gents of the AI gooning world, I'm tired of the slop I have to sift through in each of the sub-threads to get to the best quality stuff. Hence, I think it's worth us making our best of the best thread. I'll post mine straight after I've kicked off the thread. My proposal is that each person is allowed to submit 5 photos each, and then not post anymore for at least a day to avoid bloat (obviously I can't stop you, so I guess just don't be a cunt). Ideally you're only submitting in the following categories: * Before and After (with a story or neat twist is best, like seeing a fatter version of themselves in the refelction, etc.) * Realistic BBW * Realistic SSBBW * Realistic USSBBW * Best action shot (not just standing there like 👁️👄👁️) Rules: * Any race of feedee/bbw/ssbbw allowed and welcome * * None of that loli stuff. Keep that away please and thank you. Adult women only.

yes I know it costs money and the creator should make a subscription model but it is really good Glutesville is my rough story the others belong to their creators respectfully I just wanna share them https://infiniteworlds.app/shared/YbFpGV https://infiniteworlds.app/shared/kKVECz https://infiniteworlds.app/shared/HFMfVT https://infiniteworlds.app/shared/wQXhNM https://infiniteworlds.app/shared/DqAHGc Ignore image needed a file

I’ve been playing with Nano Banana Pro the past few days and I’ve had a lot of fun joining two of my great loves – classic video games and all things fat. I tried to capture the style and feeling of SNES, GBA, PS1, and new 2D games. I have a few dozen images to share and it’s a grab bag of different subject matter. This thread is for everyone and all types of pixel art content: male or female, loli/shota, furs, inflation, blueberries, etc. Anything that you care to share is welcome as long as it adheres to this art style. Enjoy!

A thread for AI generated cartoon characters

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

fat mavuika

May as well get this started

A thread for famous fatties.

i've been messing around with nano banana for a while now and think its really cool send over your own requests or generated images in this thread here's a sample of what i generated.

I've trained two Loras for Z-Image Turbo, and created some easy to use Workflows for ComfyUI to use these for Image and Video generation. [Feedai Lora](https://civitai.red/models/2545806/feedai) Produces realistic small to large BBW Women. Can be used with a bunch of different triggerwords including: feedai_lora_token: the basic activation trigger dOuble_b3lly_lora_token r0und_b3lly_lora_token tu88y_lora_token: on the chubbier rather than bbw side cut3_r0und_belly_lora_token B008s_lora_token: large boobs Unfortunately the model only loosely follows these triggerwords, and tends to bias towards soft double bellies. I've found leaving out any trigger words tends to be the most consistent for getting smaller, rounder bellies. [SSAIBBW Lora](https://civitai.red/models/2545842/ssaibbw) Produces unrealistically large SSBBW Women with the triggerword ssaibbw_lora_token.