What model/lora/etc. is this? it looks great!

>>24692 Are these even ai? They look flawless

Thanks guys, I used EpicRealism checkpoint model and I made these loras myself training certain models like Aliss Bonython and few others and mixed them in one prompt.

>>24705 any chance you'd be willing to share those LoRAs? I'm always looking to add stuff to my toolkit as well. Regardless, that's some excellent work! Photorealism is an underappreciated side of all this, so I'm always glad to see other people playing in the space.

>>24709 Thanks! I agree here are the Loras I used for this pictures https://mab.to/t/NWyJbfTlETm/eu1 Mostly on 0.3-0.5 and you can combine multiple together, use ADetailer to fix faces and hands ;) Share your results please

>>24712 Thanks! are there any trigger words or useful prompt elements?

>>24709 God that third one is good, the way the jeans are wrapped so tightly on her gargantuan thighs is just *chefs kiss

>>24713 Wait I'll share my prompts: Positive: raw ((medium wide angle)) photograph of pakistani female ((solo))<lora:alissv1-06:0.5> with thick thighs, <lora:tayv1-08:0.3>, plump <lora:angelicv3-06:0.3>, long dark hair, undersized clothes, EpicRealism<lora:epiCRealLife:0.6> <lora:epiCRealismHelper:0.7>, Negative: epiCNegative, watermark, text, ((open mouth, teeth)), (((big boobs, cleavage, busty, nude, naked, nsfw,))) cartoon, painting, illustration, (worst quality, low quality, normal quality:2), mirrors, chinese, ((blurry)), fake, (((text))), (((watermark))), wrong anatomy, bad anatomy, extra limbs, ((bindi)) ADetailer: pakistani female, pretty, subtile make up, eyeliner wing, mascara, brown eyes I use 2M Karras or SDE Karras, 20 steps, CFG scale 5

>>24712 Not bad! Used alissv1-06 for this one; I like the little details it adds to skin. First image is the raw initial generation, and the second is after running my workflow on it. I'll definitely play around with the others soon and report back with my findings.

>>24713 BTW when I have a good seed I use the hires fix upscale

>>24717 Nice! :)

>>24712 Maaan, that's awesome, good work! Really great to see more folks pushing to improve the realism. The results you get with non-fat checkpoint look awesome. Using 'angelic' lora on a quite a semi-realistic checkpoint. Who's the actual name of the lady used for training btw? :D

>>24750 https:// coomer. su/onlyfans/user/angelicgiantess for the angelic Lora

>>24843 Nice. Thanks! Was not aware of her. And the 'curvy' LoRa - is it curvybabes ( https://bbw-chan.link/bbw/res/149634.html ) ?

>>24866 curvy = curvydelightxoxo

>>24880 thanks for info and thanks for share! your loras work very well, good job meng

>>24712 Any chance we could get a re-up? Would be greatly appreciated!

Could you generate some cute asian BBW girls?

>>24938 Here are some you might like: >>22279

>>24949 They are good, but they are too big for my tastes.

>>24951 What? I don't understand what you are trying to say?

>>24938 yes

>>24958 >>24959 I hope my future girlfriend looks like one of these girls. Could you make more please?

>>24938 Here are some chubby attempts. The first two still look more on the 2.5d side, but adding filmgrain and photograph to the prompts in the latter two really help with the realism

It is possible to make stretch marks on belly and small amount of cellulite too?

>>24979 These girls have cellulite. An excessive amount on some of them actually.

>>24959 The last pic is a top class, Sir! Would love to learn more about your workflow if you don'd mind. Do you use Auto1111 web UI or Comfy? Which model do you use? How do you add film grain?

>>24692 more arab girls plz

Reup of the Loras I trained: https://mab.to/t/zaM1jceKZe0/eu1 I trained one model with stretchmarks called yoki, this is an result of using that lora. I use automatic1111 and most of the time epicrealism model, then I upscale with hiresfix and put the picture in photoshop. I use dehancer to make it look like a little bit more like an actual photograph and put filmgrain on it aswell with that plugin

>>25068 Its nice could you generate more of that? does it can generate stretchmarks on the butt? Can it make round bellies too?

>>25068 Thank you so much! They work great! I'll post some of my outputs later on when I get the chance

Could definitely use more ssbbws

>>25091 Here's a few outputs from the past day, I've barely messed with it tbh. All inpainting results, I don't really do txt2img

>>25063 some imperfections but they're arab hehe

>>25205 this is purely halal, awesome work mate

>>25068 Any chance for a reup?

Bump

these are amazing, more arab girls plz bump

>>25068 +1 on re-up!

>>25068 It might be worth just upping it on Megaupload. Not like anyone's going to try to take it down. Or put it on civitai - that place is full of weird mutant sex dragons so why'd anyone go after something as simple..

>>25068 what the hell, that's excellent. Is anyone taking down the loras? Might be worth putting it up somewhere permanent.

>>25203 >>25205 make an OF and collect infinite amounts of oil shekels

how do you use loras? wtf are they??

If anyone is interested, I have a request. Can anyone generate a realistic sumo wrestling woman?

where should I reup the Loras?

>>25436 These are so good, do you think you could do some bigger sizes? Either SSBBW or like skinny upper half and fat lower half would be cool to see ; )

>>25436 Just put them on Civitai (https://civitai.com/). They make it super easy and that's where most people put there stuff. Another option is HuggingFace (https://huggingface.co/).

>>25436 wow, really impressive work. the first one is just pure magic >>25443 +1 put on civitai

I will look into civitai to upload the loras

>>24959 >>24958 Could you do some more east Asians please?

>>24692 Could you generate some chubby/fat Japanese girls with apple body shape? If possible making the pictures look like candids would be great as well.

:D

Dropping some generations of mine that I've enjoyed to keep the thread alive.

>>25508 Can we get a re-up please, these loras are an absolute gold mine and I accidentally deleted them 😭

>>25068 These are incredible results, please do re-up if you are able!

I'm gonna try and make my own aliss lora, more news later if it works out

>>25865 guys, this was surprisingly a success. will be uploading to civitai soon

just a thought, what other models deserve loras? thinking models with unique builds. might try taytay next

Cooked this one up today. not as chunky, but I still find it good

here are my loras for aliss, not OP btw just some models I trained by myself https://gofile.io/d/pNrKHg

>>25796 Nice stuff! Are you using Pony or SD1.5 based checkpoint?

>>24692 >>24708 >>24958 >>24959 >>25203 >>25205 >>25436 >>25437 >>25508 These are so realistic and I’m gonna lose it

>>26044 bruh have you seen a woman before

>>24692 These almost look like they have film grain. Is that intentional?

>>24712 Can we please have a re-up of the LORAs? Can't believe we had a master show up, show us some of the best AI fatties around and then disappear into the ether.

>>26268 Hey I am sorry to keep yall waiting, I had no fun creating these pictures anymore so I took a break, i don't know how but I can't get them as nice as before. The pictures im generating now just look fake and I dont know what causes this. But I can reup the loras maybe some of you can get nice pictures with them https://mab.to/t/jOaV30U54mb/eu1

>>26765 I mean, you've got the original images, look at the prompt, loras used. If you haven't updated any of your models, no way you can't get the same result once again. I use the same seed all the time, with identical models you're going to get identical pictures back. Do you use tweakPNG? small utility that reads png and allows you to look at the prompt that SD always embeds into the png..

>>26765 Could you please upload again? Didn't have access to my computer to check.

>>26774 I think i'ts kinda working again, I reinstalled SD and lost all settings and stuff also the original pngs

>>26905 I love how good your model is at generating belly rolls and hangs. I'm also very much into the double belly with extra fat lower belly aesthetic. I'm mostly using open art though and their models really struggle with that look. You either get s beach ball, a very wide yet somehow still flat belly, or an abomination made out of vertical flesh folds and several belly buttons 🤣

>>26905 these are gold man. what app do you use to do them?

>>27014 it's SD 1.5 with epicrealism and a bunch of loras. I tried it out, yeah, it kinda works but holy shit I forgot how bad 1.5 is with staying with the prompt. I feel like it's only good for inpainting, 95% of the time it makes some weird monstrosity unlike PonyXL which does it 15% of the time. Might be worth re-making those loras for PonyXL. How many images did OP use to make them ? It's not weeks of GPU going full tilt right?

>>27057 what about FLUX? have you tried it? it looks really impressive regarding realism and prompt adherence, so if you have some experience in training loras, why not giving a try FLUX.dev?

>>27060 1) it's not "flux.dev" you faget 2) I checked it out, it's nothing great. Certainly at generating sexy photos it's not better than pony xl, nor that great in prompt adherence.

PonyXL without any of these loras, with a skin realism and pregnant detailer lora. It's not quite right but the skin detail is not bad. Also extra pissed because gimpshop is being completely unreasonable and hiding tool options window.. so I can't fix the navel. Upscaling takes forever and it messed it up..

just leaving this one here for the little "faget" >>27091: https://civitai.com/models/683557/flux-bbw-women

>>27443 Great stuff dude, any adjustments to your model or prompt recently?

>>27550 thanks dude not really ;) I will post some more

more larger generations

>>27443 You should do more bbw Asian woman: Korean, Chinese, Japanese, Vietnamese

>>28384 those are all the same

ChatGPT estimated Bea to be aged 18, 163 cm, 130 kg, neck circumference 45-48 cm, bust 130 cm, waist 135 cm, hips 140 cm, WHR 0.96. It described Bea's body thus: "Body Type and Shape: • Apple-shaped: She carries most of her weight around her midsection, with a prominent, rounded belly that extends outward and hangs slightly, Her upper body (waist, chest) is fuller compared to her hips and legs, which are slightly narrower in proportion. • Voluminous: Her overall size is large, with a soft, abundant appearance in all areas, particularly her torso • Full-figured: Her body is generously proportioned, with fullness in her belly, chest, and arms. Round: Her midsection, particularly her belly, has a soft, circular shape that defines her apple-shaped figure • Bulging: Her belly appears prominent and bulges outward, giving her torso a spherical look. • Soft: The texture of her midsection and body seems soft and doughy. with visible layers of fat, • Thick: Her waist is wide and thick, with multiple folds and a large circumference that contrasts with her somewhat slimmer hips. • Heavyset: Her body exudes a sense of heaviness, esp. around her midsection. • Protruding: Her belly extends forward and appears to rest over her thighs when seated, creating a noticeable hang or belly apron. Pillowy: Her belly and arms have a soft, cushion-like quality, with a notable lack of definition, contributing to her overall roundness. Midsection Focus: • Layered: Her midsection shows multiple fat rolls or folds, particularly in her seated position, emphasizing the softness and abundance of fat in her belly, • Overhanging: Her belly hangs slightly over her waistband, creating a "belly apron" effect, typical of an apple-shaped body. • Wide: Her waist is broad and dominates her torso, creating a visual width that makes her midsection the most prominent feature of her body." Does Bea look realistic? Do you agree with ChatGPT assessment of her?

google's ai is surprisingly good at this stuff

>>28565 Great work. Could you please offer a prompt for those so that we can take a crack at the filter?

>>27442 Omg dude, please please share a guide/loras for us smooth-brainers on how to create images like yours. These are the best AI images I've ever seen.

>>28600 Heres one of the prompts I used real candid photos taken on bad quality camera. in the first photo there is s e x y black-haired pale american beautiful college-aged woman wearing a cute, sed uct ive witch halloween costume. she is pudgy and overweight, bellyfat hangs over waistband. her belly has gained weight. taking a mirror selfie. in the second photo it shows her side profile.

>>28646 Thanks man. Fun doing that one, and just writing in the "second image" that she's fatter. It does a good job keeping the AI person consistent between the two images.

Can someone bbwify hannahowk

I keep getting this on Google ai I'm still learning how to generate certain kinds of images, so I might not be able to create exactly what you're looking for yet. Also, I can't help with photorealistic images of identifiable people, children, or other images that go against my guidelines. If you'd like to ask for something else, just let me know! Any ideas how to fix

>>28791 Yeah, is there a trick to it? It seems to hate anything about weight/bellies when I give it prompts. I've tried Gemini and ImageFX in the test kitchen.

Google is so good

Not bad.

>>29295 how?

Yeah, Google does these very easy

>>29545 Does google have text to image? What prompt are you using tho?

>>29545 Send a link to the google ai