/abdl/ - Adult Baby - Diaper Lover

For Lovers of Diapers and Ageplay!

Index Catalog Archive Bottom Refresh
Options
Subject
Message

Max message length: 0/12000

files

Max file size: 32.00 MB

Total max file size: 50.00 MB

Max files: 5

Supported file types: GIF, JPG, PNG, WebM, OGG, and more

E-mail
Password

(used to delete files and posts)

Misc

Remember to follow the Rules

The backup domains are located at 8chan.se and 8chan.cc. TOR access can be found here, or you can access the TOR portal from the clearnet at Redchannit 3.0.

8chan Karaoke Night!

8chan.moe is a hobby project with no affiliation whatsoever to the administration of any other "8chan" site, past or present.

AI Generated Diaper Porn Baby 03/29/2024 (Fri) 14:33:02 No. 35729 >>43665
Old Thread Not Bumping >>29801
Can I requesting two giant size male babies between the ages of 1 and 4, both about five feet tall, with one baby having short black hair and black eyes and one baby with short brown hair and brown eyes, both with slightly chubby bodies, and wearing only plain white diapers, standing, full body, smiling, anime style. Keep it SFW please
(3.04 MB 4032x3024 IMG_1793.jpg)

>>43452 Something based off of this, please.
Counter request: >>42933 more like these please, muh dick!
(165.18 KB 480x640 HyunVideo_00047.mp4)

hyvid is p. good
(634.78 KB 480x640 HyunVideo_00052.mp4)

(557.26 KB 2432x1664 home1.webp)

(721.25 KB 2432x1664 ground.webp)

(693.45 KB 2432x1664 desk.webp)

(728.68 KB 2432x1664 mat.webp)

>>43613 Here's more. Anything particular? Just did a few fast gens. >>43452 This will take me more time. You mean giants? Nothing else?
>>43452 Seems like it is not that easy to do without using OpenPose or something similar. Keywords such as baby change the composition of the whole image, and giant_male isn't doing much but adding giants on top of the other characters. I might try composing a picture (background: houses, foreground: normal sized characters scaled up) manually as you can remove the background very easily with Inspyrenet Rembg, but with text alone, one would probably need a fitting LoRA.
>>43654 Something like that. I mean a regular baby, but the same size as a normal human.
>>43654 Do you have any models for western cartoons/comics?
>>43654 Unf, that's the stuff >Anything particular? Just did a few fast gens. I have pretty simple tastes: light bondage (handcuffs), desperation (banging on a bathroom door, etc), getting teased (especially by younger characters/boys the same age). I also tend like long black hair more than short brown, but it doesn't really matter.
(628.13 KB 2432x1664 swing.webp)

>>43694 Thanks, that's some scenarios I could try to play with. First tries with light bondage weren't too nice, the faces usually show some agony and the eyes turn weird, but maybe that can be fixed with other tags.
It pains me that this is one of the only threads on the board with worthwhile OC coming out of it and yet it still falls off the first page ;_;
For Illustrious or NoobAI-XL, does anyone have any names of artists that naturally do ABDL images? Apparently they work better when an artist is mentioned, so I figure starting with one that has diapers normally would help start the generation off on the right foot.
(6.37 MB 10752x1231 00001-4117849903.jpg)

>>43786 For illustrious I'd say it's more about the model itself. The more "normal" checkpoint knowledge it has merged or trained on top of it, the more you get bad "safe for work wholesome cut toddler diapers" results or it converges towards not knowing it and making it like weird panties. Attached is the models I currently have downloaded, Falafelmix is the only one that has stayed in my list since it came out, and several of these have not been throughly tested yet for whether or not I want to keep them currently. Trying to merge a better realism model myself using SaltedPonyV5 that doesn't compromise Illustrious versatility, but I think the community is now ramping up on realism merges so they'll probably get it working nicely way before I do. DPM++ 3M SDE [Align Your Steps GITS] - 30steps masterpiece, best quality, highres, absurdres BREAK 1girl, stocking, female, woman, pose, diaper, big diaper lowres, worst quality, bad quality, bad anatomy, jpeg artifacts, bad composition, 2koma, 4koma, comic, multiple views
>>43786 I created some LoRAs for Illustrious-XL of an ABDL artists such as: Kuma Dasai, cakies22, cumbiology, merunyaa, omufujoshi, Mika hime, Popokin, alice99narumi https://civitai.com/collections/6545822
>>43943 Very nice. Did you train it on WAI-NSFW? I'm not getting as clear results from other checkpoints.
(173.70 KB 2432x1664 santa.webp)

Santa checking if you've been naughty or nice
(1.44 MB 1024x1024 001.png)

(1.32 MB 1024x1024 002.png)

(1.36 MB 1024x1024 003.png)

(1.39 MB 1024x1024 004.png)

(877.75 KB 768x768 ComfyUI_03154_.png)

(749.25 KB 768x768 ComfyUI_03133_.png)

(821.17 KB 768x768 ComfyUI_03129_.png)

(730.03 KB 768x768 ComfyUI_03110_.png)

(807.02 KB 768x768 ComfyUI_03126_.png)

messed around with illustrious a bit, super fast to run and theres some decent LORAs on civit ai already, definitely reccomend for a non-realistic look
>>43997 You might want to use the standard SDXL VAE, you have lots of white spots in your images, and it could also be why the results are very grey and dull.
>>43999 Not 'op' but curious. Is that a base Illustrious VAE issue? I haven't seen that using whatever VAE red dot pops out of the node.
>>43999 im using comfyui with and have literally never touched the VAE node, not even sure how to lol
>>43946 It was trained on base Illustrious XL 0.1 model. I know about this problem and I need to fix the dataset. This is mainly caused if there is no "close-up" tag in the prompt
Any advice for keeping background characters out of diapers when I add them into prompts? I tend to create images that have 1 or 2 characters focused with people in the background, but I want to be able to more freely control which character is wearing a diaper. Still new to this and having some trouble.
The new Kling Image to video model works pretty well although it's only a few seconds of video on the free tier. This was from a flux.dev image I made and kling did the rest.
(59.21 KB 1408x768 1735208353986.png)

(48.67 KB 1408x768 1735183563099.png)

(77.07 KB 1408x768 1735182934449.png)

(75.26 KB 1408x768 1735182928865.png)

(83.15 KB 1408x768 1735182920158.png)

Best i can do with a phone
(61.96 KB 1408x768 1735182644198.png)

(55.52 KB 1408x768 1735182472073.png)

(77.85 KB 1408x768 1735182517350.png)

>>44053 FINALLY the rule of 3D is over, fucking about time.
Have any of you tested NoobAI (especially v-pred 1.0) and know how to set it up to make it work well (sampler, scheduler, cfg rescale) or even know what settings to give LoRA training?
(984.18 KB 896x1152 Lora_00003_.png)

(1.41 MB 896x1152 Lora_00015_.png)

(1.36 MB 896x1152 Lora_00017_.png)

(960.29 KB 896x1152 Lora_00027_.png)

>>44186 Training on the EPS one gives worse results than training on base Illustrious. Results are the same quality on both NAI-XL branches so no need to adjust anything for lora training. The recommended settings on Civit provide fine results. The only thing that seems a little different is that results tend to be better when prompting an artist name as well. Easiest way is to look at some of the example image prompts and see what artists people are using. You don't need "artist:" even though plenty of people use it. Just the name is fine. Some names with styles that I liked are "cato monocatienus, re-ghotion, fumio rsqkr, merunyaa, zd_1995, OlchaS, sakimichan, massakasama, bigdead, and aetherion". I wrote a random prompt generating script, rather chatgpt did, that uses danbooru tags that I used for sample images. You can see the comfyui workflows I used along with the settings on Civit. Here's the 4 for the attached images. masterpiece, best quality, newest, 1girl, (diaper:1.2), aetherion, star-symbol-background, hair-between-eyes, heart, grin, standing, long-hair, crop-top-overhang, makeup, long-sleeves, open-clothes, brown-eyes, feather-coat, looking-at-viewer, short-hair, brown-hair, hair-ornament, hand-on-own-cheek, cleavage, green-eyes, japanese-clothes masterpiece, best quality, newest, 1girl, (diaper:1.2), bigdead, blue-hair, standing, long-hair, sky, black-thighhighs, tail, gloves, makeup, long-hair, cow-ears, hair-between-eyes, wind, smile, sleeves-rolled-up, puffy-long-sleeves, choker, side-ponytail masterpiece, best quality, newest, 1girl, furry, (diaper:1.2), merunyaa, smile, armpits, large-breasts, miniskirt, pumps, jacket, sky, feet, smile, breasts, corruption, looking-at-viewer, skirt, long-hair, toes, black-jacket, brown-shirt, animal-hood, sweater, short-hair, purple-eyes, anthro masterpiece, best quality, newest, 1girl, (diaper:1.2), facing-away, (fumio rsqkr:0.75), blazer, short-hair, small-breasts, spotlight, glasses, flower, ponytail, arms-at-sides, hair-spread-out
(1.29 MB 896x1152 Lora_00007_.png)

(859.84 KB 896x1152 Lora_00023_.png)

(1.43 MB 896x1152 Lora_00010_.png)

>>44189 >>44186 Totally botched selecting the right images for the prompts... Here are the other images and the other prompts. You should be able to figure out which is which. masterpiece, best quality, newest, absurdres, highres, 1girl, (diaper:1.2), (cato monocatienus:0.9), re-ghotion, facing viewer, full-body, yellow shirt, breasts, green hat, short hair, blonde hair, wavy hair, grin, hands behind back, outside, sunny day masterpiece, best quality, newest, 1girl, (diaper:1.2), zd_1995, OlchaS, sakimichan, sakimichan \(style\), sleeveless, gradient-hair, blue-eyes, red-hair, purple-hair, shirt, two-tone-hair, tail, frown, gloves, solo, bra-visible-through-clothes, blush, nipples, multicolored-clothes, striped-clothes masterpiece, best quality, newest, 1girl, (diaper:1.2), (massakasama:0.4), off-shoulder, chinese-clothes, bdsm, collarbone, striped-clothes, outdoors, purple-eyes, solo, navel, pink-background, black-hair, thighs, jewelry, head-tilt, short-sleeves, blue-hair
>>44107 >>44106 omg these are top notch

Index Catalog Archive Top Reply 481
246
785

Forms
Delete
Report
Quick Reply
Drag files here to upload or
click here to select them