HentaiKami 110 Posted May 18, 2023 Share Posted May 18, 2023 On 5/4/2023 at 3:09 PM, omuai said: Wow, you really are diaper AI pioneers in here After some unsuccessful attempts last summer, I became interested in AI generated pictures again this year. I've had some good results using Stable Diffusion and the anime DiaperAI model available on civitai.com (a lot of thanks to whoever made this or the models that were mixed for it!) and that encouraged me to dive into creating a diaper LoRA. After more than 40 attempts I'm still mostly trying to figure stuff out, but some of the results are nice in my opinion. Figured it would be fun to try to put a diaper on @ihcah's old favorite image. Here's my attempt. I couldn't get it any brighter, but at least the diaper somewhat fits the lighting conditions inside. I used my own diaper LoRA + AOM3a1b (by accident) and lots of img2img/inpainting. Then I added the tapes and smoothed out some weirdness and did another few rounds of inpainting. Added an anime picture with a similar setting and a somewhat more omorashi beach picture just because. For pee, the LoRA "peeingSelfV2" was used. Awesome! Any chance I could get your Lora and some of the prompts you used? Those are phenomenal! (Gonna try to train my own as well, but 1) I am a noob, and 2) 8 gb of VRAM-) I didn't know PeeingSelfV2 really was a LoRA -- I was told to add it into model checkpoints, is that not correct? When you do inpainting, do you just mark the parts that seem off and regenerate? Sorry if it's a lot of questions, I would really appreciate it if you would give some advice. ^^ Quote Link to comment
ihcah 485 Posted May 19, 2023 Author Popular Post Share Posted May 19, 2023 Padded (and wet padded) Taylor Swift lingerie shoot : ) I used a public LoRA for her face, and used a woman modeling lingerie as the base image for ControlNet to get the pose, then my custom pads LoRA. I'm getting better at figuring out how to use this LoRA effectively, fortunately. ral, MalibuClub, xixi and 4 others 5 2 Quote Link to comment
ihcah 485 Posted May 20, 2023 Author Share Posted May 20, 2023 And I know that’s not true to Taylor’s figure 👀 but of course my figure-base was a lingerie model image (taking her overall shape via controlnet), then I added wider hips and other bits to perfect her, then the face as Swift, and then the pad Lora & tags. what a world we live in, where I can ask the computer for a fantasy of Taylor Swift with hips and a pad, and have it generated for me so easily yellowsailgg and ral 2 Quote Link to comment
Epicman 2 Posted May 20, 2023 Share Posted May 20, 2023 Some attempts of mine. Tried many combinations of AnimeMix_v3 and diaperai_v2. Also playing around with peefusion_V2. Next I want to try to train my own LoRA up next. nappyslave1 and rachelkirwan 1 1 Quote Link to comment
Optimalhentai 39 Posted May 21, 2023 Share Posted May 21, 2023 used an anime model with an abdl LoRA. Added detail and changed a little along the way nappyslave1, rachelkirwan, omuai and 1 other 3 1 Quote Link to comment
HentaiKami 110 Posted May 21, 2023 Share Posted May 21, 2023 Let me just drop a few more. Wish I could get a more consistent anime style with better regular/medical diaper results as well, but oh well, I guess it's just a matter of waiting. omuai, yellowsailgg, Peena and 2 others 4 1 Quote Link to comment
Jimbob19080345 0 Posted May 21, 2023 Share Posted May 21, 2023 (edited) The faces look horrifying in the beginning stages Edited May 21, 2023 by Jimbob19080345 (see edit history) Quote Link to comment
HentaiKami 110 Posted May 22, 2023 Share Posted May 22, 2023 22 hours ago, Jimbob19080345 said: The faces look horrifying in the beginning stages Well, the free online stuff still sucks a lot of arse when it comes to faces, though they're getting better. The trick is to run stuff locally and inpaint until you get something that doesn't give you nightmares and/or make you piss yourself - even though I'm sure many of us wouldn't mind the latter. Optimalhentai 1 Quote Link to comment
ihcah 485 Posted June 2, 2023 Author Share Posted June 2, 2023 (edited) Quick update: I now have a new Mac with a silicon chip, so I can generate images 100% locally with no cloud GPU required. It's not quite as fast, but fantastic to have this locally! I did a quick local generation of Princess Zelda wearing her royal pull-up, to celebrate. Edited June 3, 2023 by ihcah (see edit history) rachelkirwan and MrIzzay 1 1 Quote Link to comment
ihcah 485 Posted June 2, 2023 Author Share Posted June 2, 2023 (edited) And just for fun: Saturday Morning cartoon Zelda ; ) "Excuuuuse me, diaper princess" Edited June 2, 2023 by ihcah (see edit history) rachelkirwan, MrIzzay and xixi 2 1 Quote Link to comment
omuai 21 Posted June 3, 2023 Share Posted June 3, 2023 (edited) On 5/18/2023 at 9:13 AM, HentaiKami said: Awesome! Any chance I could get your Lora and some of the prompts you used? Those are phenomenal! (Gonna try to train my own as well, but 1) I am a noob, and 2) 8 gb of VRAM-) I didn't know PeeingSelfV2 really was a LoRA -- I was told to add it into model checkpoints, is that not correct? When you do inpainting, do you just mark the parts that seem off and regenerate? Sorry if it's a lot of questions, I would really appreciate it if you would give some advice. ^^ I uploaded a similar LoRA to civitai this evening (ID 83342, omuai diaper lora). I've trained at least 40 diaper LoRAs with different settings, but the first ones were really bad. I've also experimented a lot with various settings (learning rates, dimension, batching, etc). The one I uploaded to civitai is pretty close to the one I used for the pictures I uploaded here, sadly I can't upload the same one because the .safetensor contains too much meta data that I'm uncomfortable to share. Doing LoRA is possible with 8GB of VRAM, I didn't have more when I made my first good LoRAs. When I use inpainting, I try to mark the area as closely as possible, yes. There are some ControlNet addons that can make inpainting better (i.e. closer to what you might want, especially regarding anatomy if it is off), but sometimes the more random approach of not activating it is better to achieve better results after more time/generations. The PeeingSelfV2 LoRA I have is just usable by itself. I have never had to merge anything into checkpoints. On 5/16/2023 at 3:14 AM, ihcah said: @omuai nice to see others getting into this hobby : ) I saw the civit models too, but wasn’t too interested since I’m more into the niche of “incontinence panties / pads real women wear” rather than ABDL-like products. When you trained your own LoRA, it sounds like it went well. Did you use regularization images? In my last revisions I did, seems to help. I’m also curious if you used ControlNet. For my LoRA, I don’t feel that the results are great as far as overall composition if I only use prompts or image-to-image. But if I take a photo of a woman in panties, convert to a “canny” sketch and just draw a single line or modification to suggest the diaper, the model will produce lovely results. The images I posted today were based on using ControlNet with just a normal picture of a couple of Hooters girls in their shorts; I mostly used canny in ControlNet, with a slight hand edit, then my LoRA understood and created the realistic diapers. I’m sure there are better workflows. And the tools keep getting better. Yeah, we need more people that play around with this, there's just not enough diaper images! :) I actually noticed that you were more into incontinence panties/pads after I had already sent off my post, but I didn't dare edit it because I wondered if the post would get approved later because of it. Sorry for the confusion :) Regularization images have never worked well for me. In the beginning I had one instance where I thought it improved things, but my first LoRAs were generally pretty bad so it might have just been better by random chance. I've read a lot about creating LoRAs, and the common wisdom seems to be that regularization is not worth the effort or actually bad, and considering that LoRA actually add some layers to the matrix, I wonder if that isn't to be expected because to get the same images, those layers would have to revert to go inactive again, maybe? I like ControlNet, there's many great features to play around with. It totally depends on what I am going for, though. I think it is great for getting the background right or to do certain poses, but it's difficult to get the bone length right with openpose and anime characters. I'd say I sometimes use ControlNet canny or something else to get the background/surroundings right, then I might img2img, and then I alternate inpainting with SD-webui and with my drawing tablet and Krita because it is so much easier to guide the AI to fix certain areas if you just try to draw what you want and refine it with AI. Edited June 3, 2023 by omuai (see edit history) MrIzzay 1 Quote Link to comment
ihcah 485 Posted June 3, 2023 Author Share Posted June 3, 2023 (edited) Very different approach here, trying to start towards the style of old men's magazine dirty paintings, by the pin-up masters of the past (Elvgren, etc). This one is still rough but I really like it... call it "wet wife wheels home" Alternate combinations: Edited June 3, 2023 by ihcah (see edit history) rachelkirwan and nappypants 2 Quote Link to comment
ihcah 485 Posted June 3, 2023 Author Share Posted June 3, 2023 4 hours ago, omuai said: The one I uploaded to civitai is pretty close to the one I used for the pictures I uploaded here, sadly I can't upload the same one because the .safetensor contains too much meta data that I'm uncomfortable to share. Interesting, I’ve never shared models so I haven’t looked into the contents of the safetensors, are you saying that it preserves some info beyond the weights? Quote Link to comment
omuai 21 Posted June 6, 2023 Share Posted June 6, 2023 On 6/3/2023 at 10:52 PM, ihcah said: Interesting, I’ve never shared models so I haven’t looked into the contents of the safetensors, are you saying that it preserves some info beyond the weights? As far as I know, various scripts that float around the net to train LoRAs have an option to save some data about the training into the metadata portion of the .safetensors. It's enabled by default for some of them. Removing some info changes the hash of the file, so it is not trivial to do so without a good explanation of what portion of the file is being hashed. It obviously can't be a hash over all data, as that would include the hash inside the metadata itself, which is generally not doable. Maybe it's all but the hash itself but I didn't bother to find out after a few failed attempts to find the information somewhere. When I checked the info, it had a creation time and training finishing time, and that lets you guess the hardware that was used. Image tags are counted, so if you ask deepbooru and a few mostly unique tags fall out, people may be able to make good guesses about which images have been used. For me, the timestamp + potential hardware info were the main reason to not want to share metadata. Quote Link to comment
ssdfg12 16 Posted June 8, 2023 Share Posted June 8, 2023 rachelkirwan and PattyWets 2 Quote Link to comment
Peena 165 Posted June 16, 2023 Share Posted June 16, 2023 (edited) Knowing nothing will make my actual waifu, I went in with a highly rated iPhone app anyway to see what I could get. She turned out very cute except for the arm! Edited June 16, 2023 by Peena Added more (see edit history) PattyWets and HentaiKami 2 Quote Link to comment
HentaiKami 110 Posted June 19, 2023 Share Posted June 19, 2023 On 6/16/2023 at 9:17 AM, Peena said: Knowing nothing will make my actual waifu, I went in with a highly rated iPhone app anyway to see what I could get. She turned out very cute except for the arm! Never say never. Who would be your waifu? I might see if I can find a LoRA and give it a shot. ;)) Quote Link to comment
Peena 165 Posted June 20, 2023 Share Posted June 20, 2023 16 hours ago, HentaiKami said: Never say never. Who would be your waifu? I might see if I can find a LoRA and give it a shot. ;)) ENA from the show of the same name. If there is a model she will give you nothing but trouble and I already know it! 🤣 HentaiKami 1 Quote Link to comment
HentaiKami 110 Posted June 20, 2023 Share Posted June 20, 2023 1 hour ago, Peena said: ENA from the show of the same name. If there is a model she will give you nothing but trouble and I already know it! 🤣 Ah, I see the issue. Yeah definitely aren't any LoRAs I can find- Unfortunately, my PC is not beefy enough to train LoRAs. 😞 Quote Link to comment
Goodnites98 13 Posted June 20, 2023 Share Posted June 20, 2023 Loving this stuff! Quote Link to comment
Peena 165 Posted June 22, 2023 Share Posted June 22, 2023 On 6/20/2023 at 2:53 AM, HentaiKami said: Ah, I see the issue. Yeah definitely aren't any LoRAs I can find- Unfortunately, my PC is not beefy enough to train LoRAs. 😞 Yeah if I had anything better than my laptop and ANY knowledge of the process I’d make one of her. But I don’t 😭 HentaiKami 1 Quote Link to comment
HentaiKami 110 Posted June 22, 2023 Share Posted June 22, 2023 52 minutes ago, Peena said: Yeah if I had anything better than my laptop and ANY knowledge of the process I’d make one of her. But I don’t 😭 I feel ya' there. Not only is this AI stuff complicated as heck to get decent at- it's also super expensive. Well, one COULD rent a better GPU (cloud computing), but eh, 'dunno how safe that is/ anonymous it is, so I won't mess with it for now. 😅 Quote Link to comment
Ajax7408 341 Posted June 22, 2023 Share Posted June 22, 2023 On 4/17/2023 at 10:47 PM, ihcah said: This one is from a paid service online, sort of exploiting their demo a bit by rotating my VPN / browser id so I can keep submitting text to it --for that reason I don't want to print their name in this thread, since they're a newer company that might google themselves regularly, ha (and this use is definitely against their TOS). I'll DM the name. There are some offline models but so far I haven't found any quite as good... but if anyone finds one, let us know. Sooner or later the open source models will beat the paid services for voice just as they have for everything else. Can I get a DM also? Quote Link to comment
rachelkirwan 13,626 Posted June 26, 2023 🌟 OmoOrg VIP Share Posted June 26, 2023 On 5/19/2023 at 4:19 PM, ihcah said: Padded (and wet padded) Taylor Swift lingerie shoot : ) I used a public LoRA for her face, and used a woman modeling lingerie as the base image for ControlNet to get the pose, then my custom pads LoRA. I'm getting better at figuring out how to use this LoRA effectively, fortunately. These are so hot!!!! nappypants, Diaperdaddy84 and Snorri 3 Quote Link to comment
ihcah 485 Posted August 6, 2023 Author Share Posted August 6, 2023 (edited) quick pull-up Tifa since I haven't posted in this thread lately Edited August 6, 2023 by ihcah (see edit history) imfac and ral 2 Quote Link to comment
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.