/inf/ - Inflation

Pumped up, billowing, blueberries

BBW-Chan is supported by simple text or static image ads from a-ads.com.
Please consider whitelisting us in your adblocker if you enjoy your stay!


Mode: Reply
Name
Subject
Message

Max message length: 9999

Files

Max file size: 10.00 MB

Max files: 6

Captcha
E-mail
Password

(used to delete files and postings)

Misc

READ THE *RULES* BEFORE YOU POST!

[ / / ]

Stable Diffusion body inflation art Anonymous 09/14/2022 (Wed) 13:06:51 Id:3ba4ae No. 61940
I'm having fun making inflation art from ai artist dream studios https://beta.dreamstudio.ai I use Dall E mini to make the art and then went to dream
>>75814 Did that slightly with img2img and worked very well. Iā€™m currently training a hyper network for it too
>>75447 Any chance if anyone here knows where I can find BiggerGirlsV1.2? I can't find it on github.
>>76163 https://civitai.com/models/2664/bigger-girls-model it's been linked a few times now I think
Recently remembered about other formatting keywords to change the appearance of the medium the AI renders it as and tried out anime screencap. I noticed it mostly generated nearly the same girl each time (though still had some other random character generations of course since long blonde hair wasn't in the prompts), so I chose the ones that looked similar with each other and ordered it like a sequence of sorts If anything it reminds me that there really wasn't any sort of body inflation or weight gain focused hentai's out there, or if there is I just haven't heard anything about them, lmao
just started using ai based on the stuff that was put here, anyone have any tips on how to write prompts good?
any shylily inflation? she is a whale and i think her outfit being so revealing and tight would be good. i think people over on the vtuber thread would appreciate it. (me, i am the one who would appreciate it)
tupidi
(418.48 KB 640x512 Untitled2.png)
>>76784 The raven haired model is cute!
>>76235 Which model did you use to create these?
(630.86 KB 576x768 tmp99e8jlg1.png)
(923.43 KB 768x896 tmpqtojqp3v.png)
(949.11 KB 768x896 final.png)
(906.83 KB 768x896 tmpk96zjha3.png)
(948.20 KB 896x1024 tmp3_j71mrm.png)
(872.00 KB 768x960 tmpwjbb6hlb.png)
Didn't check back on this for a while because I kind of cracked it, got bored, and moved on. But should probably answer a couple of questions that people asked that I never got back too. (I hate it when people leave shit hanging). Here's some examples of where I'm up to again(I did a bunch of generations here, all of these used no image to image). I included 1 that isn't inflation as well just to demostrate on the High quality ones that I've made some progress as well (basically pretty close to proving the original annon who said that 'these at best would match the quality of the shit the community draws - and other then a few errors I'm within the ball park of 'good' artists in general. I can get realistic to artistic (close enough) in everything but completely spherical quality - the other anon figured that out already so I won't bother unless he wants to share some info. >>69267 Nearest neighbors. train half your model using the match to get it to understand a loose concept - then move it towards the specific. The idea is if you have a big belly, you seed the model with pregnant in the tags then, switch it out after a couple of training steps to a lighter weight (stop the model, redo the tags, resume training). What the training model is doing is it's actually (removing) the things that you list in the model, but also looking for similarities at the same time. Basically it's a balancing act towards that. For example, in the standard model of SD you'll list "big breasts" that always leads to 'voloptuous hips" the trick is basically you do a step wise training to move the embedding slowly to an 'isolated concept'. This is caused by 'concept bleed'. You'd (if your using the NovelAi / waifu diffusion model, a funny thing happens whe if you use the oppai tag, and the boobs tag together you'll end up with 4 breasts because of this, as they tag them as seperate items due to oppai loli (thin hips, big breasts)). Basically - be VERY specific in what your training it for... the more you describe the model, the better it will be as a training image. It's good to glance at the dictionary of terms - then get very specific. if your curious - read up on how the tagging section of the model works for recognition of tokens in the language phase. People are focusing on the images - not the 'words' section. basically what you list in your model will be related to what you get out. >>69412 this was done via the novel AI leak. Use DIIM for best results. 32 sampling steps and a custom embeddings that I can't remember for the life of me. I used several and alot of options. Right now - as a major aside - that's important is people haven't checked the 4chan work that's been done on this - the hyperpreg model actually contains flags for (belly inflation) (body inflation) and if you merge it and train (slightly) retrain the model with other models you can actually get pretty 'realistic' results without actually having to train a whole new model from scratch - you can actually get models that are NEARLY in range of good models that can be trained further with a leep start. (you can litterally save do hundreds of thousands of dollars of stuff on a few bucks). Otherwise for general embeddings - it's better to have 4-5 images that are almost identical, rather then 500 that are disimilar. You use about 2/4 embeddings for a concept (things), 16 for an artist 'style'. link for their model database: https://rentry.org/sdmodels - worthwhile checking out. >>71405 I didn't, this was done via soft seeds of embeddings. Because if you check how stable diffusion works below the hood it's a noise algorithum. What your looking for is basically stuff that creates a large 'circle in the noise' of what will be generated at an early step and transition that into a real model. Basically in the above cases I was using a micro embedding trained of a few artists. When I do training, I have an early 'soft bail' - if the embedding doesn't look like I want in 3-4 steps at a low go at only something like 0.05/10/10k I bail on training the model. The reason is std will hard pull if you've gotten the concept correct 'isolated' (see above) into what your training it for. also another trick that I've learned recently as a side note - is you can actually train a hypernetwork in something 'better to 'learn' it - then a different network to 'apply it'. this is worth it's weight in goal - especially if you merge (say hyper preg, balloon diffusion, 1.4, and other models). also never use STD::1.5 - it's trash - they removed the titties for it. >>71929 I honeslty have no idea, usually what I do is run the model and see if it does a 'hard swing' on the outputs (a new epoch every 100-200 steps) and a test image. The algorithumn should hard filter towards the target if you've set up the data / embeddings correctly in the setup. A GOOD data set normalizes fast, very fast, then will move away again. In the first 1000 steps you can see generally if you're getting 'what you aimed for'. Generally you want to use images that are similar for simply stuff and low 'noise' (similar). So a single pose of 'inflation' only requires 1 image. (also make sure you name you keyword nonsenes not to get overlap as well.
(904.78 KB 768x896 tmpllbwh2nd.png)
(726.69 KB 768x896 tmpvozukv4f.png)
(1.13 MB 768x896 tmpttcj5w1v.png)
>>77196 Dropped some images on submit just to show the range I can get now.
If yoi guys wanted to draw young girls pregnant why didn't you just pay a professional artist? A commision?
(746.69 KB 640x896 tmpwg_t_v_b.png)
>>77198 Because it's fun? Has productive value? and at the end of the day, minus the errors, because of the fapping I can pretty high quality concept art for other uses? Are you stupid?
>>77201 >I can pretty high quality concept art for other uses Judging by this statement alone I have to conclude that you are indeed a whole lot more stupider than I ever imagined. Wayyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy stupider. Maybe my mom was right. Maybe I am much more intelligent than you guys.
>>77202 Right... Let me guess, arts degree and a minor in chemistry relating to acid / base reactions results?
>>77203 No that's too old school for me. Let me guess, do you enjoy watching Netflix Originals? Honest question though, what are your thoughts about microwave ovens?
>>77202 About the same amount of thought your going to be getting in commissions.
(521.81 KB 512x768 FnHuV-3XwAkuUYp.png)
>>77225 I see these jagoffs have migrated here too. You guys really that frightened of AI that you have to roam the internet, harassing people wherever you find them?
New recommendation: try the Deliberate v1.1 model: https://huggingface.co/XpucT/Deliberate These are all done using that model alone. I entered no artists' names in these; it's the model's default style. Note that you have to turn the number of steps way up for this model. I'm talking like 90 to 120 steps.
I should also point out OrangeMixs even though I haven't tried it yet: šŸ”— https://huggingface.co/WarriorMama777/OrangeMixs The version to try would probably be the NSFW or even "Hard" version of AbyssOrangeMix2. Try blending it with SD (yes, even 1.5) if you want a touch more photorealism. I haven't tried it yet but if anyone wants to, it looks promising.
Wanted to point out some posts in another thread: >>77328 Also Deliberate v1.1. Amazing the level of photorealism you can get from it with enough steps (90 to 120).
>>77323 sir, this is absolutely unbelievable, really great work, hats down happy to share more results? or some hints on the prompts you used?
(1.03 MB 3024x4032 FullSizeRender (15).jpg)

Delete
Report