/bbwai/ - bbwai

Stable Diffusion, Loras, Chatbots


10.00 MB max · 6 files · PNG·JPG·GIF·BMP·WebM·OGG·WebP·TXT
Captcha no cookies?
Read the rules before you post.
Advanced (canvas, flags, deletion)
Drawing: × size canvas
(For post deletion)
[ Index / Catalog / Bottom / Logs / RSS ]

AI Audio Smut Audio AI Voice Acting
There's a terrific website that converts text into voice using AI (and has some free usage that resets every month). It's actually pretty rad because you can either write your own stuff, or even use other people's stories if you'd like to hear it read aloud by a reasonably convincing female. https://beta.elevenlabs.io/ I like the Bella voice personally, though the Eli one can be good too. Love to hear some other originals, I've attached one I've been crafting.
46 posts and 3 images omitted.
Does anyone have any good ssbbw music they've generated?
Been messing around with Suno to make some Alternative Music about being with an immobile woman from a lesbian perspective because us lesbian FAs / Feeders need more representation lol let me know what you think and if I should keep going for a whole albums. https://suno.com/s/8vDitEVxBosQJFK0
Please tell me anyone knows the source on this one? https://drive.google.com/file/d/1Za7dtCV0pzw-822_bn_NHZ3109sEVTc_/view
>>40641 This is fantastic! Keep going!
>>1621 Which voices do you have cloned?

slob pit Anonymous
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
362 posts and 164 images omitted.

Bottom heavy bbw ai Anonymous
post girls with huge ass/thighs any size is good, slimthick or ssbbws just make the ass big
382 posts and 866 images omitted.

Open file 7.35 MB, 1080x1920

Open file 116.43 KB, 2144x2944
kinda nuts how this thread started in 2023 and you can see the progression of AI through the thread

Ai lara Anon

Open file 2.37 MB, 1024x1536

Open file 2.45 MB, 1024x1536
You don't need to make new threads every goddamn time.

Anime/Game Style WG Sequences? Anon

Open file 2.73 MB, 1536x1536

Open file 2.69 MB, 1536x1536

Open file 2.79 MB, 1536x1536
I've been playing around A LOT with comfyui lately and I just finished this 19 part sequence of Hu Tao from Genshin Impact (mimicking a certain artist's style). PLEASE don't spread these around because I don't want the artist to encounter any issues at all! This is honestly pretty blatant plaigarism and the last thing I want is for the artist to suffer for it. Just figured I would share because I'm pretty happy with the results! (some issues here and there but overall pretty good imo!). Here's parts 1-3!
9 posts and 16 images omitted.
stitched this together using Grok

Open file 60.89 KB, 463x640
>>43592 site doesn't seem to let me upload gifs so here's a webm instead
>>43593 couldn't help myself, decided to extend the thing

Z-image Thread

Open file 1.21 MB, 1152x896
Here is a prompt:由四个平凡无奇的瞬间组成变胖对比图,展现爆肥带来的从脸到身体道四肢的所有部位的肥满化巨变。 丰腴微胖->超重显胖->大胖妞->SSBBW。 保持画风服饰与动作统一,强调变胖爆肥逐步变化。女主长相十分普通但是身材极其丰乳肥臀。从左到右排布四个阶段。 现场采访的截图。主角是17岁的少女,穿着暴露,手持话筒,纯真微笑。偏侧面角度。 第一张图:.主角身材有曲线,肉感丰满,整体微胖丰腴。字幕:我要增肥 第二张图:主角身材发福变胖,轮廓圆润了很多,全身明显发福。此时女主体脂率上升,体重达到超重级别,身材走形,显得更加肥满。腿变粗变胖,并且脸部变大变圆,有显著的双下巴,肥肉覆盖每个部位,肚腩明显。外观显胖了。字幕:还不够胖 第三张图:在保持画风不变,角色整体、细节设定不变的条件下,角色到达肥胖的体型。身材完全走形,但还未到达ssbbw的程度。 脸要更大更圆更双下巴,补充肉鼓鼓的脸颊。 腹部至少要有两层游泳圈,靠下方的那层会更加向外突出。字幕:理想身材 第四张图:人物爆肥,胖得轮廓圆润丰满,高体脂率高体重,赘肉肥硕向外溢出,体型庞大肥满,四肢粗胖,臀部腿部和手臂胖得没有缝隙,大肚腩圆滚滚,面部又大又圆胖乎乎的,脸颊过度饱满,整体膨胀肥胖。极端严重肥胖,夸张extremely obese,远超最胖级别的SSBBW。字幕:控制不住
357 posts and 490 images omitted.

Open file 3.69 MB, 2048x2048

Open file 3.99 MB, 2048x2048
由两个平凡无奇的瞬间组成对比图,展现爆肥带来的从脸到各部位的肥满化巨变。保持女主眉眼与构图完全不变,强调变胖爆肥变化。画面要求超高分辨率,严重过曝,极其平凡无奇。几乎没有构图可言,略带运动拖影。随手一拍的快照,有轻微仰角、镜头略偏斜的构图。画面带有些许噪点,镜头有不易察觉的灰尘。低饱和度。氛围真实而朦胧。 圆润微胖丰满>极端严重肥胖像是相扑。 女主在左图圆润丰满,整体微胖丰腴,已经有所发福,脸圆圆的有肉感,有小肚腩。 在右图东亚女主完整穿着指定的衣服,长相十分富态温柔,饱满圆脸,双下巴明显且厚实,五官很日系,冷白皮清透反光。非常肥胖圆润。面部宽大肥腻,脸颊胖得过度饱满挤压五官,脸圆得赘肉溢出,面盘宽胖像是球形,有着厚实的三层下巴,女主彻底超越想象的肥胖堕落,胖得比最胖最肥的情况还要胖体型更圆更庞大,身材完全走形。人物爆肥,胖得轮廓圆润丰满,高体脂率高体重,赘肉肥硕向外溢出,体型庞大肥满,手臂和腿部十分粗胖,赘肉胖得相互挤压,下身胖得比腰还粗,圆滚滚又肥又大,腹部至少要有两层游泳圈,靠下方的那层会更加向外突出。面部又大又圆胖乎乎的,脸颊过度饱满,整体膨胀肥胖。极端严重肥胖,夸张extremely fat and massive。
DV 16mm tape camcorder handheld footage feel. Point of view of CHASE holding the camera directly in hand. Maintain hand shake, misaligned framing, delayed focus pull, clumsy zoom in/out, occasional self-cam framing where the face gets cut off, and imperfect shots that lose the subject. Every shot is CHASE holding the camcorder herself, filming in selfie-cam or first-person style. The camcorder itself never appears on screen. LOOK: DV 16mm tape camcorder footage look. Soft, slightly blurry digital tape quality, faint tape noise, highlights that bloom slightly under gym lighting, auto-exposure that flickers subtly, muted color contrast, realistic skin tones. STYLE: Energetic but casual gym-vlog tone — upbeat between sets, a little breathless, genuine laughs, motivational mini-commentary. Handheld throughout, quick cuts, alternating selfie and mirror shots. Character CHASE in her 20s, long straight black hair tied up in a high ponytail, elegant yet lovely Korean features, glowing skin with a light post-workout sheen, big eyes, slim athletic build. Wearing a modest long-sleeve athletic top and loose-fit joggers or leggings, fully covered arms and torso, sneakers, a small towel around her neck. No jewelry. Setting: A gym in the early evening — mirror wall, weight rack, a mat area, water bottle on a nearby bench, a few machines visible in the background, soft overhead lighting. Storyboard: Front-facing selfie arm's length, she walks in with bright smile despite slight breathlessness: "Okay guys, quick workout vlog today!" Handheld whip pan from weight rack to mirror wall to mat area, back to her face, off-screen playful: "Gym's pretty quiet right now, perfect timing." Medium handheld by the mirror, she checks form mid-stretch, adjusts ponytail: "Just stretching before I start." Macro insert shallow DOF, close-up on her hands wrapping around a water bottle cap, condensation on the bottle, ambient gym sound only. Medium handheld tracking her, she demonstrates a light squat or lunge, glances at camera between reps: "Just a few of these and I'm already feeling it." Snappy cut sitting on a bench, she takes a sip of water, wipes face with towel, exhaling: "Okay, water break, definitely needed." Quick punch-in tight selfie, cheeks flushed, hair slightly damp, she grins at lens: "This is the sweaty part nobody shows you." Arm's-length selfie finish, she stands, towel over shoulder, gives tired-but-happy wave and thumbs up before reaching to end recording: "Alright, that's a wrap — see you guys!" Realistic gym sound, natural breath, casual laugh, 16mm tape grain, soft bloom, slightly imperfect framing. 画面要求超高分辨率,严重过曝,极其平凡无奇。几乎没有构图可言,略带运动模糊。随手一拍的快照,有轻微仰角、镜头略偏斜的构图。画面带有些许噪点,镜头有不易察觉的灰尘。低饱和度。氛围真实而朦胧。 东亚女主完整穿着指定的衣服,长相十分富态温柔,饱满圆脸,双下巴明显且厚实,五官很日系,冷白皮清透反光。非常肥胖圆润。面部宽大肥腻,脸颊胖得过度饱满挤压五官,脸圆得赘肉溢出,面盘宽胖像是球形,有着厚实的三层下巴,女主彻底超越想象的肥胖堕落,胖得比最胖最肥的情况还要胖体型更圆更庞大,身材完全走形。人物爆肥,胖得轮廓圆润丰满,高体脂率高体重,赘肉肥硕向外溢出,体型庞大肥满,手臂和腿部十分粗胖,赘肉胖得相互挤压,下身胖得比腰还粗,圆滚滚又肥又大,腹部至少要有两层游泳圈,靠下方的那层会更加向外突出。面部又大又圆胖乎乎的,脸颊过度饱满,整体膨胀肥胖。极端严重肥胖,夸张extremely fat and massive。
>>43279 The first one is pretty nice actually

Props, Objects, Outfits & Scenes Anon
Share props, objects, outfits and Scenes-Locations that can be used as references for generating AI Content

Open file 390.03 KB, 437x512

Open file 2.05 MB, 896x1200
Quick Example using Melinda Gordon from Ghost Whisperer, Made in Google Flow. Adding images as references in the prompt box: (Melinda, wearing same piece as image), solo, single panel comic, realistic digital artwork, holding Frappe, Morbidly Obese, large fat belly, walking out of Starbucks
I love these!

Open file 336.64 KB, 784x1168

Open file 406.02 KB, 784x1168

Google Flow Anon

Open file 76.79 KB, 1280x720
Are any of you using this? I know on the face of it, it uses Nano Banana 2 or Pro, but what I've found is that it's significantly more lenient than ImageFX or NanoBanana have ever been as standalone applications. I'll post what I've been able to do, but holy moly, the things this application let's you get away with (some things might have to be spammed a little), and how much it understands context are a bit mindblowing.
160 posts and 406 images omitted.
>>42310 "Clothed before, naked after" seems to be the winning line. It doesn't seem to mind making obese women naked, but it has an issue with thin women naked.

Open file 704.04 KB, 1376x768

Open file 1.42 MB, 1280x720
Fat goth 2077

FG a.i. cutscene and artwork edits for female characters Anon
A thread for edited images generated with any a.i. site or tool for you to share and add to any fat mod for each fighting game, including street fighter, tekken, king of fighters, dead or alive, and more

Realism AI Video creat0r
anyone else has tried Minimax H3?
Locally image/ref -> video, with my RTX 5090

Anon

Open file 3.49 MB, 5312x2988
Make a differenet pose showing off her pantyhose
Not how this works, retard.

Male Expansion Swap Anonymous
a thread focused on replacing instances in media and fanarts where a male character expands with female characters expanding on their places instead
39 posts and 99 images omitted.

Fat Figurine edits Anonymous
Ik this is a pretty niche thing but it’s something I been fixated on for a while.
5 posts and 5 images omitted.

Open file 1.86 MB, 1038x1516

Open file 1.06 MB, 1254x1254

Open file 88.62 KB, 1024x1024

Open file 1.59 MB, 1082x1454

Open file 1.62 MB, 966x1628
>>43526 that 4th one is peak

Fanvue Anon
Anyone here signed up to fanvue? OF for AI characters sounds nuts but this creator makes some pretty hot tiktoks https://www.tiktok.com/@foodaddict0?_r=1&_t=ZN-99NYYNjEm5W https://www.fanvue.com/charlotte.r

I trained local image generation models for generating BBW and large SSBBW images and videos. Local BBW Image & Video Models

Open file 3.03 MB, 1536x2048

Open file 2.72 MB, 1536x2048

Open file 2.59 MB, 1536x2048
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. Each come with their own workflow (attached to the images on CivitAI), containing a wildcard prompt which will generate an infinite combination of BBWs and scenarios. The image generation workflows first produce a rought draft, and then refine this in a second polish stage. This allows for more control over the size of the BBWs without compromising realisitc detail. The strength of the Lora can be adjusted individually for the two stages, for e.g in the SSAIBBW workflow the rough draft has very poor detail, but can produce extremely large BBWs, which the model otherwise struggles with, and then can be polished to be more realistic in the second stage. The video generation workflow (attached to the videos on CivitAI) is designed to take the images and produce varried 5s videos in a batch. You select the first image in your input folder, and select the number of runs, and it will iterate through all the images. I use a NSFW lora, as this produces much more realistic jiggling. The higher the resolution, the better the detail, but this also results in much longer render times. I run these workflows on my 8GB GPU (64GB RAM), the images take ~2min, and the vidoes ~4min. I usually just queue a bunch, and let it generate overnight.
6 posts and 7 images omitted.

Open file 2.27 MB, 1344x1728

Open file 2.59 MB, 1344x1728

Open file 2.31 MB, 1344x1728

Open file 2.43 MB, 1344x1728
v2 of Feedai has now been uploaded to Civitai: https://civitai.red/models/2545806/feedai
My retarded ass can't figure out how to import the workflow into comfyui. How do you?

Open file 2.30 MB, 1344x1728
You just download this image, and drag and drop it into ComfyUI, it will open the workflow. You'll need to install the missing nodes (Z-Image Turbo LoRA Loader) before running it.
Oh yeah, this is a pretty good lora. I used it some. Interesting to know about the times, for me it generates ~1536x1536 in about 45 seconds or so, using a two stage workflow.