>>11282 Ah also, I used a Succubus Covenant [Pony] lora for the above images. https://civitai.com/models/432436/succubus-covenant-or-game-cg-style If you're curious about the specific generation parameters, they're embedded in the metadata of the images.

https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Optimum-SDXL-Usage Didn't know this existed but it is also very useful.

>"being employed to do office work by the elf OL boss in another world" these isekai titles have been getting awfully specific huh?

>>11285 though not as good as "conquering heaven with my bitchy demon girlfriend"

>>11286 I like how her bright skin masks the usual AI glow/oversaturation. Aside from looking very carefully at details, I'd have problems judging if it's AI

>>11282 Can AI do extremely specific fetish stuff in the style of a particular artist yet?

>>11290 Depends heavily on what you mean. There's a chance that one of the models understands that concept, or you might be able to find a lora for it or related concepts on civit. Alternatively, you can even train your own LORA. I was able to train one with only a few GB of VRAM but SDXL loras might be a bit harder since the models are much larger. I'll look for a good SDXL lora guide in a bit.

>>11292 Also, you can mix and match loras with varied results, but it seems better lately on SDXL/Pony. So if you can find or make an artist style lora, and then use a fetish lora, you should be fine.

Not exactly monstergirl though she is a humonculus. But here are some results by messing with Asanagi, then Hews style lora.

>>11286 I'd prefer "conquering hell with loyal angel gf". So Helltaker with some extra elements. >>11297 That's totally Kuro and Illya. But it looks pretty good, the technology came a long way. Pretty soon commissioning a specific artist with a notable online presence wouldn't even be necessary, as you could just train a model on his pics and have unlimited free generation. I wonder how the necessary amount of training data will change in the future. As in, how few pics would future models need to understand a specific artstyle or how to draw a specific object. Right now human artists need only a few pics of a specific thing to know how to draw it, and they can probably make do with a single pic when it comes to artstyle (tho of course more would be better).

>>11359 yeah, of course. Both Illya and Kuro are homunculus, i do enjoy fucking with around. Even generated a few Hataraki Ari based Chloe pics, may upload it later

>>11364 do post them while at it, also tell what artist are imitated in pics 1-2 and 3.

I genned some using NAI Anime v3, but they might be a little heavier than some anons prefer but hopefully someone likes them.

>>11367 and two more, I have a lot but these six are the best I feel.

>>11366 I just mixed Chloe with Felicia from darkstalkers. Didn't specify what artist it should copy

>>11282 >SDXL model called Pony Diffusion. Is there a quickstart guide to what I need to start doing this?

>>11404 I basically tried to make the thread introduction as close to a quickstart guide as I could. I might write a proper one when I have time. That first github link explains pretty well how to install A1111, but if you have any problems feel free to ask and I'll try to answer when I check the thread. A1111 has been having a few problems with SDXL for a while though, so some problems are expected. There are like 2k "issues" / bug reports on the github so I'm pretty sure the dev just gave up trying to look at them all. Once you've installed A1111 webui, you need to install a version of CUDA (if you have an NVIDIA GPU, no idea about AMD) so that your GPU can do AI calculations. https://developer.nvidia.com/cuda-12-1-1-download-archive https://developer.nvidia.com/cuda-11-8-0-download-archive 12.1 should be the correct version, but other installs have used 11.8. I think SD A1111 by default today uses Pytorch with CUDA 12.1 but I'm using 11.8 at the moment because it's more stable for me. Try 12.8 first and if that doesn't work ask here because that's a hassle. After that you literally just download a single file (the pony model or another one) from Civit and put it in models/stable-diffusion and start up the webui, then load it in through a model switching tab in the top left. Go to the txt2img tab and prompt anything then it should work. If it gives you an error check the console and it's usually a vram or memory issue which means you need to use the optimization args linked in the thread or add/increase a system pagefile (harddrive memory). There's another alternative that is supposedly more stable and has higher performance, but I don't think it has any or as many extensions and has flowcharts instead of GUI. Didn't mention it at first because it's probably only better once you have a good understanding of stable diffusion. https://github.com/comfyanonymous/ComfyUI

>>11427 12.1*

>>11427 I will get around to this soon. At least buying nvidia finally paid off.

It's everything anyone could have wanted in a monster girl.

It's remarkable how often I can start something only for the site to go down into maintenance.

>>11282 >It automatically detects faces in your picture and inpaints them to keep them from looking terrible. Any advice on using this?

>>11454 Not sure what you mean by "using this" so I'll just cover everything I think of. First, you install it in the extensions tab using the url of the github repo and then restart your webui. I recommend just installing all the extensions before restarting or you have to do that multiple times. In txt2img where you generate your images, you'll find the adetailer tab below the seed value. You are given four tabs to work with, and on each you can choose a "detector" model. The detector model will look for specific patterns in an image, crop them, inpaint/fix them, and paste them back onto your output. SDXL usually only needs help with faces. I have found that the default model, face_yolov8n.pt, works well enough for this. Below the detector model is the prompt for inpainting. It works just like the normal prompt. Usually the default works fine but it's good to use a specific prompt if you want to highlight a specific detail during inpainting. There are face, hand, whole body, and I think a few other types of model depending on what you want to inpaint. The other tabs don't really matter but I'll go over them briefly. Detection - this determines what the model considers to be a part of what you want to be inpainted. The threshold determines how much like a "face" (or whatever you want to find) has to be for it to be cropped. The ratios and offsets allow you to change what is cropped by the ADetailer if you're looking for something specific. Inpaint- You can try messing with this if you get bad results. You can change the denoising value (essentially how much your original output should be overwritten when inpainted, higher is more) and also resolution to see if it changes your results in a way you like. ControlNet - if you're doing a full body inpaint, you can try to use controlnet to keep the same positions after inpainting, otherwise it's much less reliable. It basically feeds the original image as a reference to control net and then inpaints with that. If you're interested, see what I mentioned in the top of the thread about controlnet.

>>11457 https://github.com/Panchovix/stable-diffusion-webui-reForge Also, I ended up switching to this today. Not sure if I recommend switching to it for anyone else yet but at the very least it is far, far more stable than A1111 for me. A1111 crashes constantly on my PC, I originally planned to mention webui-forge, which was the original version of the above, but it has apparently been discontinued from its original purpose recently and will now have a lot of experimental features (and therefore bugs), so I never tried it. Reforge has no crashes (yet), I can actually use my pc while sd webui is generating 4 images at a time in the background. A1111 used 50GB of ram due to a memleak that hasn't been patched for some computers since SDXL support was added. Only downside so far is that some extensions seem to be broken, fortunately civitai helper and adetailer still work.

Made an experimental lora for black alice. Took about 3 hours to train. It's far from perfect but at least it gets the outfit and general appearance right. Faces don't go very well but with ADetailer you can smooth out the problems. https://gofile.io/d/AlAVef

>>11463 I have discovered that the earlier versions of the lora actually provide better faces and seem to be a little better. If anyone expresses interest I'll upload those some time later today.

>>11464 Wow, that's an amazing looking Black Alice, ignoring the fingers. Shame that I have an ancient PC that can't into AI.

>>11457 I mean I can see it doing the painting but I'm not even sure if it's changing anything.

>>11466 If the faces are already pretty good it probably won't appear to change much. If you have live preview on (showing you something while it generates) then it'll show you if it detects a face, drawing a square around it with text like "face 0.8" (80% certainty) and then it'll inpaint. If you're looking for something specific try changing the adetailer inpaint prompt, denoising strength, and resolution. If it just flat out doesn't detect the faces try changing the lowering the detection threshold or changing the detection model.

>>11474 Sometimes the face can also be corrupted by the LORA. The black alice lora has that issue above, probably because I over trained it. I made an Ilias one after uploading since they take like 20 minutes to build a dataset and 3 hours to train in the background. Not ready to post that one yet but it had the same issue. If you use a custom prompt it won't use the lora for the inpainting unless you specifically put in which may have better results You can also change the lora weight by changing the number in the lora identifier Ex: <lora:monstergirl:0.8> vs <lora:monstergirl:1> That can reduce deformations caused by the lora

>>11475 On further reflection the face issues on mine might actually be my fault. I'll probably try adding close up shots of the faces from the images to the training data. With only full body shots I guess it makes sense the faces would be bad. Still looks good enough right now with inpainting though. I'll release my current one or a new one I train tomorrow if it looks better.

>>11476 Sorry I've been very busy lately. I couldn't get it working quite right but I think it's even better with adetailer now, and the body. Using 2d and the "detailed face" tag probably makes it better. https://gofile.io/d/IJPyHx It's trained in epochs which you can consider a measure of training time. The ones without extra numbers are "less trained" which can reduce artifacts from over training. Each higher number is trained for longer and the one with no numbers are trained for longest. I included the last three because I couldn't decide which one I liked best.

All of those were made using Novel AI and their "NAI Diffusion Furry V3" (I know, I know, Furry bad yadi yada but the model is very sound) I am still very much a beginner yet I do enjoy the results after messing with it for less than 48 hours. (They are to my taste so it might not resonate with you, I like the angery and rapey kinds)

>>11676 Looks pretty good to me. I've never had too much interest in models that can't be run locally because it feels weird having corporations spy on your usage of the models I've noticed this thread has stagnated a bit, probably because of the high hardware barrier for entry and the uncanniness of AI sometimes. Hopefully, that'll change soon enough. A new AI image model released within the past week or two called Flux. On it's own, the model is too big to run even on a 4090, but it's structured in a way that let people make optimized versions with mimimal quality loss that can even feasibly run on a gtx 1060. Seems even better than Stable Diffusion by a noticeable margin, and in a completely different league with understanding prompts and accuracy. Only problem is it lacks finetuning for anime and has no nsfw capabilities, because it seems they either intentionally avoided it or tried to prevent the model from making it. But people have already gotten it to generate naked people, but not sex. Give it a few months and someone will probably make loras for it.

>>11688 Thank you! I was in the same boat too, until I realized that not everyone was rocking a 14900KF/4090 with 64 gigs of ram while also rocking some fierce autism and wizard powers. (let's be real, to have the real good results it's a rather arcane and in depth skillset) Since this is mostly used by fury, I'm quite positive that even if someone checked the stuff I make I would be the vanilla fag, it's still very annoying but the results are there, if you're into niche stuff it's probably your best bet before either Flux or Intel release Lunar Lake and Nvidia Blackwell, those are dekstop solutions with dedicated AI compute units on them.

>>11693 I'm not sure how good my stuff is, really. It's certainly much better than when people first tried doing nsfw on Stable Diffusion. I think I'm desensitized to small artifacts because of how bad it was for nsfw and anime when sd 1.0 came out. **Warning and disclaimer: attached picture may or may not irreversibly kill any and all boners. It's like if xelvy came back from the dead and his creations inbred for ten thousand years and fell in a vat of image artifacts. You have been warned.** And no, I didn't ask it to generate multiple heads. It kind of just used to do that. Also, updating on Flux, people have already created nsfw anatomy loras, blowjobs, and anal. Surprisingly no cowgirl or other vaginal sex yet. They're moving impressively quickly. I'll post a tutorial on how to install Flux (once I figure it out myself) when I feel that the NSFW makes it worth it to switch or dual run with sdxl. Blackwell chips are completely a joke, don't even bother with them. Modern NVIDIA AI chips are sold for over 10x production cost. Blackwell chips are estimated to price at around $30-40k msrp, and you have to get a quote from NVIDIA, can't just buy it because they're corporate chips. Your best bet is waiting for the 5090 release next year if you're interested enough. That's what I'm doing, but I'm afraid scalpers will bot them all before I get my hands on one. I'd say AI is a bit less autistic to install locally than before, the biggest problem is just that python is probably the most insufferable software I have ever used, bar nothing. I'll forever be sad most AI is built on it. Maybe I'll make a guide at some point on how to deal with python environments and bs. Half the errors I've had with AI are exclusively because python is awful.

>>11699 Me neither, I'm a starter with this model and this prompting method, I assume it's quite good since I was able to make that while barely trying, it's been 5 days and the results are quite good if I dare say so myself. As meymey as it sound, I always had troubles with offline models and for whatever reasons I tend to break anything coming from GitHub, for a rather cheap price I have unlimited generations with this service, already made 2000 pictures, none of them were trash (I can't share most of them here, my tastes aren't meant for this place) I would like it very much if you could somehow streamline the whole Flux process please, I'm as surprised as you are with the lack of cowgirl/riding. Sorry, that's what I meant, the 5090 and other consumer grade hardware, for many reasons I have a Quadro at home and it's... finicky with AI and in particular with Stable Diffusion. I agree with you, Python (mostly PyTorch really) account for half of my problems, for me there's a before and after GitBash methink, but still one day, perhaps we will get all the dependencies in a single .exe and not have to hunt down some arcane .bat from questionable website :^)

>>11702 Yeah, still looks pretty good to me. I just don't know if that's because I'm desensitized to ai or not... I don't blame you for having trouble with some of the Github installs. Sometimes I'll pull updates from a github repo and a commit will have irreversibly broken a feature and contributors won't fix it until weeks later with an "oopsie". A lot of times changes aren't actually tested so the userbase is used as quality assurance. The tard rage I feel when I have to spend hours fixing those errors myself makes me think I'm autistic. Good thing I know a bare minimum of python coding and pip, but I can't touch any of the AI related functions. Theoretically it's probably possible for me to pack stable diffusion webuis into exe files for everyone, but it would have to have a pytorch version packed into it built for a specific version of CUDA. That pytorch version in the exe would A. have to be compatible with your pc B. have a version of cuda compatible with the graphics cards of every user. I'd probably have to make an entire FAQ about how to tell if you have to manually setup the webui The exe would also likely be over 3 gb because of all the python dependencies built in (especially cuda baked pytorch) https://civitai.com/models/666326/first-edition-sex-positions-rough-versionnsfw-flux-lora?modelVersionId=745718 Someone finally released vaginal sex positions for Flux today. I think it's worth me at least taking a look at now. Flux only does realistic people, but one of the first loras someone released was an anime style lora so it doesn't matter. Not exactly sure how monster girls would go. Anyways, I'll take a look at it and maybe post my findings when I have free time, probably this weekend. Perhaps even an arcane bat from a questionable capybarachan thread will be coming to an area near you! Or not... depends on how hard I think it is to configure any of this, or if I can get it working. I do recommend the RTX 5090 when it comes out, but even the RTX 2080TI or 3080TI can work well these days. You can get the former for $200-400, and it can generate a batch of 8 Pony images in about 10 seconds, excluding adetailer inpaints. I assume the 3000 series will also rapidly depreciate in value after the release of the 5000 series.

>>11708 Unfortunately, I cannot get FLUX working yet. Works fine enough alone but occasionally has crashes that seem to stem from being out of memory. LORA usage spikes memory drastically, and a single LORA takes 50 seconds to load for me per generation, likely because of how Flux works differently from SDXL. It seems we need to wait for one or multiple things A. Community made Flux variant model with built in NSFW and better concept support so you need less loras B. More optimized, stable lora code that does not crash and works quicker C. $20 RTX 4090s Flux probably could work right now but unfortunately for me I only have 32gb of vram and a 2080TI. Pity. Hopefully it's more optimized soon, I'll check again in a week or two.

>>11709 32gb of RAM* I do recommend switching over to Forge as they have stabilized and finished the breaking changes they did previously. SDXL should work great on it. It is also the only webui that I know of that currently supports flux (unless you count ComfyUI but that's less user friendly), but forge's flux support is, well- as I've said previously. The install process was actually remarkably easy. I just download a zip and ran a batch file and it didn't even have to download everything because it comes with a localized python environment in the zip file. https://github.com/lllyasviel/stable-diffusion-webui-forge Pony SDXL should work easy on stuff with 5-6gb of vram.

>>11708 That's pretty neat! I would enjoy very much to see that, my only "skill" is being able to screw with RPGmaker, perhaps with a good enough model I could make "scenes" for a potential game, maybe even involved the anons on capybarachan? that would be cool. A 5090 with 64 gigs of ram is on my bucketlist once it's released, I don't know what CPU I'll go for, depends if the 9950X3D is better at chugging along or if the Bartell lake from Intel with 12p cores and a 8400mhz+ of ram will be better, we will see. >>11709 That's a bit sad, but it was a bit too early anyway so I don't mind waiting if you're willing to spend some of your precious time on it. >>11710 Once I'm back home I'll give it a spin and see if my autismo will break it or not.

>>11714 Hope your computer didn't catch fire lmao If you're having trouble usually it's easiest to install a fresh python environment or you have the wrong/no CUDA version installed. Crashes with no error are usually caused by OOM or your cpu/gpu overloading. OOM crashes are obviously also caused by OOM. Anyways, back to what I was originally posting about- I've been keeping an eye on Forge and there are at least three new code changes related to Flux and LORA optimization. Looks promising, though I think I'll wait a while before trying it again. Either way, kudos to the Forge dev for being so on top of things. Used like 80gb of virtual memory excluding my VRAM, insane. I think the one time I even managed to get a lora working it didn't work with anime, so I'm gonna wait for the tech to develop. Really hope someone makes that nsfw flux model.

>>11750 Note, forge is still worth installing because I think you can get some pretty satisfying results with Pony Diffusion (SDXL) and loras.

Continuing on this, I've found that not only can you "ehance" a picture but you can also not only "vibe transfer" but downright "image to image", it will grab whatever you give it and following what you gave it, depending on many factors will make a copy of it following your specific prompts. This lead me into a rather, rather deep rabbit hole, I'm merely emerging from it.

>>11778 From Pick1 to Pick 2, not bad at all! >>11750 >>11751 Alas, I still broke it... I'll keep screwing around with this until Flux is ready and/or I found a way (or bother my grease monkey friend) made by someone that knows how to wrangle tards with way too much compute power for their talent. I'm kind of seething that I went with 32 gigs of ram instead of 96, but I could know months ago that I would lean into AI stuff and JRPG/rep&pey stuff before hand, oh well. I'll monitor this thread with upmost attention.

>>11779 Not bad. I've kind of strayed away from img2img because I couldn't get reliable results but maybe I'll revisit it. I had better luck with controlnet but it seems unstable rn after all the rewrites. People are complaining of problems with it. I'm still beating myself up over not getting 64GB of ram yet I also can't justify buying more to myself. If I do then I'd just have to replace 4 entire ram sticks if I ever wanted anything beyond 64GB.

>>11791 Also, is there any specific way it's breaking or errors it's giving? Forge uses an absurd amount of RAM nowadays. I just configure windows to use a 50GB pagefile on one of my ssds and that kept it from crashing for me.

>>11791 It's all about the strength slider and perhaps screwing a bit with the prompts, I made another thread where I'm explaining as best as I can how to screw around with prompt, sooner or later I will have to make a list of all the tricks... someone called me out >>11782 and I explained that this thread is more about the tech monkey/hardwarepart, mine was more about prompting. >>11792 Nope, no error message, no crash, just simply vanish, it's not even in the process being stuck or anything, I don't know anon, I tend to be curse with things like that, perhaps because I'm using an heavily modified version of Window 10 (Atlas OS) there's probably some things that are screwed the wrong way (I'm mostly a gamer and I like to play those nice but horrendously optimised games)

>>11794 I don't really think I specifically intended for it to be about technical knowledge and news when I first created the last two threads. It just sort of happened that way because not many anons are active here, and my autism was left to frolic freely. Pretty sure it's like at most 4 people, and half the posts are me. Still, I do think it's an alright idea to have a thread specifically for prompts because of how cluttered this one gets with troubleshooting, news, and other nonsense. Though it's pretty much impossible to troubleshoot anything over an imageboard so I might create a server on a discord alt at some point or something. As for using AtlasOS- I would say you are very, *very* slightly completely and totally out of the standard support range for AI. It could be unrelated to AtlasOS but yeah that definitely doesn't help. Not sure what you quite mean by vanish. If the console has any text it might give clues about what the error is. It might tell you that it fails to generate, I have no idea.

https://civitai.com/models/556479/mge-monster-girls?modelVersionId=706589 Thought this was enough to warrant its own post to the thread. A LORA on CivitAI that adds support for 30+ MGE characters to PonyXL. Kudos as always to the creator.

I spent some time on spicychat and made two bots with the following premises: Smug, confident ancient mummy princess traps you, the explorer anon, in her tomb. I also made a clumsy stalker marriage-obsessed elf who always fucks up when she uses magic, either sexily or comically. I like them both, but smug mummy is definitely my favorite. Smug mummy: https://spicychat.ai/chat/76d9a081-d4c7-4dcf-bdfe-8f356435745e Clumsy stalker elf: https://spicychat.ai/chat/c07db718-9a78-45b6-aa39-9a6b52f158f4

>>11834 One day someone gotta hook up those lewd bots to those interactive sex toys, like onaholes with exposed APIs

>>11835 someday, bro. I've made so many smug mummies the last couple days. Who knows where AI will go in the next decade? What a time to be alive.

>>11834 Had a quick chat with both. Nepta jumped straight to paizuri which was pretty swell. I don't know if you wrote it into the definition, but the first thing she did when she got a hold of my rod was wrap it in bandages, which I also enjoyed. Overall solid bot. I led the elf on for a bit before shutting her down and decided to leave it at that because it was funny, so I can't comment much on her. She's otherwise very persistent, though. Anyways, you should also consider uploading them to Character Hub (Chub), I find its free service generally makes for better conversations and users can just use their own local installs with it if they want. Spicychat's pricing is completely insane.

>>11837 Damn i had no idea about Chub, thanks man i'll look into it tomorrow night. And yeah, the bandages stuff is in the definition, but the way she uses them sometimes surprises me. I also wrote in that she thinks she invented the concept of paizuri, lol. I've been adding some non-lewd stuff slowly as well. The elf still needs work, the magic she uses doesn't always fuck up as i would like, but i like her otherwise.

>>11837 I second this, Chub is great and it also provides download files for characterts with local text models like ggufs on SillyTavern.

Thanks to the power of S L O P P A, I finally managed to make my dream come true. Behold: Slimias! I guess the results could be better because I still have no idea what I'm doing, but it's a lot of fun to fuck with.

>>12078 Yup, aisloppa is just perfect for slimes, unsurprisingly.

>>12079 Yeah, but goop can only go so far when hiding deformities, especially when introducing non-slime things into the mix. Anyways, here are a few more with some more complex concepts, some more successful than others.

necroing the dead AI thread with a fobs tribute. Couldn't get the colors exactly right though, but most of it's there.

>>14860 This came out surprisingly good, is this some kind of img2img upscaling or did you fiddle with prompts until you got the end result?

>>14870 I do a lot of prompt fiddling until i get a position or style that i like and then img2img. Inpainting usually sucks dick comparative to drawing on and re-generating the image. V3 still has the better "image reference" function and i can't wait till V4 gets it. My old strat was to use artist mixes until i get the style, and then prompt to get the position/outfit/whatever while adjusting reference strength to get the art style and retain the same character. Until i can use reference images again it's mostly a mix of which prompts work best on character and which work best on the general prompt selection. The artist and style prompting i have not yet figured out in v4 it's way different than it used to be, i didn't use one for that. Sometimes you can straight gen shit like these with enough detail. I was doing a "Slime bath service" scenario and then a "green slime in the swamp" kinda thing. What i'm trying to do is lock down a particular art style to be consistent and then generate the same girl/guy kinda deal.

>>14879 Whatever style you used for the blue slimes pic is great, it has none of the shiny artificial plastic-y feel AI pics usually have and I wouldn't be able to tell it was genned without knowing it. In comparison, the green slimes look as if they were some kind of nuclear glowing slimes, lmao.

friend made some almas

>>14965 pretty amazing how well it captured hakika's distinct "skin" sclera eye style

>>15586 >3rd pic Having a centaur in your lap doesn't sound very comfortable

Contributan the five free pics that I was able to make on feetgen.com >>15586 >Dat tongue Nice!

>>17228 >feetgen.com kek

>>17190 >sexo with centaur's upper body Rare, that's one of the good applications of AIsloppa

One repoost but it fits the set.

>>17228 you know i do find feet erotic but only in specific circumstances that rarely if ever aligns with foot fetishists most of the time .

Stumbled upon those gens on rule34 by accident and felt the need to share.

>>17612 >paws

>>17815 Based AI decided she needs to be even fluffier

I feel bad for even asking, but has anyone tried to replicate UN_DO's style?

>>18301 Your wish has been granted https://civitai.com/models/376760/un-do-style-monster-girl-quest It's a lora for Pony based models, but probably works to some extent with NoobAI and Illustrious because they all share the same base. Illustrious actually has most popular artists pre-trained in it though, so you might be able to get a result without a lora by doing something like artist:un do

>>19069 I like how the second shog has the goopy, slimy look in the background behind her skirt. Kinda nails the vibe.

>>23746 that one came out pretty damn good to be honest. I would so a slight re-run to fix the artifacting in the eyes and cover up the base of the larger horns with hair. The fins and stuff all look really excellent though. Unrelated but here's a mommy tier dark elf witch i've been working on

Can anyone recommend a good, free, AI chatbot site with lewd shit enabled? The best one I know of is https://chub.ai/, but its search function is fucking godawful. Using hyphens to denote that you want to exclude a tag doesn't work. Using quotes to force an exact match doesn't work. Searching for multiple words at once treats it as an "x OR y" search, thus showing you 99-100% irrelevant results. Sometimes you can clearly see a word in a character's profile description, decide to search for it, and the search returns only a handful of results, none of which include the profile you were just on, thus proving that even when you only search for a single word that you know exists on a profile, it won't show you relevant results. God only knows how many characters you're missing out on because of those false negatives.

>>24586 I feel like I should mention that I've also tried crushon.ai and found it equally disappointing, if not more so

I bring gifts.

i have been working on a particular style that is coming together now.

>>24676 shiny but the nutsack on first pic is oddly detailed, kek

>>24732 I use an extension for Forge, linked in the OP, to automatically re-draw certain features that get distorted at higher details. The one for the penis probably got some of the nuts.

>>24729 This is AI???

>>24903 Yeah, i've been working on a non-artist based kinda watercolor blended style.

Hora... Stop being a little bitch and let me rape you.

>>25607 >Asking for permission to rape She must be feeling generous

>>24912 >Its never been more over for us artfags. Well, time to invest into a graphics card I guess.

>>25751 I was thinking of specifically starting an AI request thread to see how far i could go with it. I've gotten a lot of good results.

>>25758 Thread OP here. When I made this thread, I never really thought that requests were specifically something that would need another thread, I considered such things included. Maybe if we just have walls of text with unanswered requests. But as long as it's like a 50:50 ratio of text to images I think we're pretty good.

Let's see... Requesting a squirrel girl in a ninja outfit. Bonus points if she's perched on a tree.

>>25794 She forgot one very important piece of camo gear.

>>25758 Fug it, lets go Rabbit girl with a button nose, hime cut, long side bangs, long hair. Swimming underwater with water goggles on. Monochrome, screentone manga shading. Nice underwater background.

>>24676 >That third pic D A M N >>24912 >That third pic Cute and funny. Literally! >>25758 >I was thinking of specifically starting an AI request thread If you're still generously accepting requests, how about Ruby Rose as a wolfgirl in a position sort of like the one in this vid, kind of like cowgirl but with one foot planted on the guy's face and the other foot's toes being forced into his mouth, with Ruby having heart-shaped pupils and an expression that's both cutesy and smug at the same time? Preferably also leaning forward toward the guy with her (massively oversized!) breasts hanging down, not leaning backward away from him the way Juri is in this vid >>25794 >>25896 >>26170 Based, prey animal girls and hime cuts are both awesome and criminally underrated. Cutesy girls turned dominant are the toppest of top tier

>>26170 Sure am buddy. It's never gonna be perfect and inevitably i'll take liberties, but i like how this one came out.

>>26195 this is ultra specific and probably difficult, i will give it a shot but it might take some time.

>>26195 i lied, it was way quicker than i thought. I put two here, the first one is the one i think is the best, the second one i think is more accurate to the request.

>>26216 fuck lol i forgot the pupils, added to the second image.

>>26216 >>26217 Thank you thank you thank you thank you thank you Your model (lora? I don't know AI art terms) even got the little hair swoops on the side of her head, and the fact that one of her bangs is longer than the other, right. You're an absolute god-king and I can't thank you enough. I want to inundate you with requests but I also don't want to be a bother. Thank you very much again!!

>>26217 >>26222 Btw I'll also gladly accept any scraps/leftovers/pics you generated that you thought weren't good enough. Literally any & all of them

>>26222 Don't worry man, i do this for fun and the requests test the limits, so feel free to toss them out willy nilly. I won't do them if it's something i'm against but otherwise i enjoy it.Specifically - I have a vague idea that if i can get a consistent style and learn some editing software (or pay a real artist to edit out things i cannot fix) that i can make a game/visual novel eventually themed on monster girls. I'm doing as much as i can in varied types to learn how tags interact and how to fix problems. I just use novelAI (funny enough, their text stuff is way worse than the imagegen and i never use THAT, which is why i tried it in the first place), there are a ton of wild ass local models and things you can use though. I think a LORA is a subset of images to dictate style/pose/characters that you can use, novelAI is just it's own contained thing.

>>26226 That's awesome! I bet you can do it I never could git gud at NAI but I'll probably give it another shot in several months, giving it plenty of time to become even better As for more requests, how about... >Wolf girl Ruby Rose with gigantinormous boobs again, breast smothering a guy with a supremely smug expression, one raised eyebrow & all, like in this 1st pic? Minus the lamia body of course. I've almost never gotten NAI to portray breast smothering in a coherent way >Wolf girl Ruby Rose with gigahueg boobs again, mostly cowgirl position but also locking her arms and legs around the guy, while kissing him with an absurdly long tongue that's shown via "x-ray" like in the bottom half of the 2nd pic? Or if that last part doesn't work out, the extreme french kiss could be implied via his throat bulging + drool leaking from between their lips >Same character, as smug as ever, with the most absurdly huge ass you can possibly concoct, hyper_ass even, facesitting facing away from the guy, and the guy is shown to be rimming her via an x-ray-style shot, if possible

>>26229 i've got work in a bit, but later today i will give these and any other requests that crop up a whirl.

>>26230 Tyvm! As for weirder stuff to provide even more variety & push the limits of the bot... >A generic, "faceless" guy like in the last pics you generated laying on his back between 2 wolfgirl Ruby Roses with outrageously huge assets, 1 sitting on each side of his face. The catch? His [spoiler]arms are trapped inside them, forced to anally fist them all the way up to his shoulders[spoiler] >The same pic as a base, now with a 3rd WGRR fucking him cowgirl position >The same pic as the previous one, now with a 4th WGRR sitting on his face, facing away from him Tbh I think it'd be interesting to give this position a name, but on the other hand it's probably never been drawn to begin with and may never be drawn/generated again, so it might not serve any purpose >The froggirl in these pics in the aforementioned poses in both this post and my 2 previous posts, >>26229 >and >>26195 / >>26216 >but without the silly frog hood on her head (I dislike it tbh) and without the goggles around her neck (I don't mind the goggles at all but removing them would make the pics easier to generate) On another note, the 1st pic is censored due to rule 9

>>26211 >I can't believe its not butter manga! also I'm a nigger that forgot to specify rabbit feet, but that's on me Very nice and thanks! Since you want to push your model, can you try generating Lamiamon pointing at a rock and laughing at it? I think it could be challenging because I don't think there's any Lora for her yet, and her design is quite complex and specific. More details about the pose, holding her stomach, closed eyes, laugh marks(?, you know, those manga rectangles that often appear when someone's laughing), head very slightly angled back. Slightly low perspective, with the rock being closer to the viewer than Lamiamon. Honestly, if you manage to generate any Lamiamon at all, I'd be impressed and happy.

>>26229 I took the ones i liked, (some of that was a little too intense for what i usually do and /AMG/ tier for the site rules). That said, i think they came out good. I'll prolly try frog girl later at some point. >>26295 that shit was impossssible, nothing even worth posting as that thing is a mish-mash of stuff that looks like other stuff to imitate other stuff. A good test but one that im not yet able to reproduce. As a consolation, have a nervous djiinn-lamia maid that i spiraled off into as a result of failing the request, and some big titty oktoberfest elves, thought you might like them as one has that manga 'surprised embarrassed' expression pretty well done.

>>26295 Anon, ask and you shall receive. Not sure how long you all have been following this thread, but waaay back when I made it, I was malding over the fact that it would probably be impossible to get a 5090. But, well, I finally got one. So I figured I'd try to figure out how to train Illustrious loras. I've spent my afternoon setting that up, and decided to use your request as a test run. I got a somewhat functional lora of this character. If you're interested in that, just say so, and I'll upload it. The quality isn't the best ever because there were less than 20 images in the dataset since this character basically doesn't exist. Here are some images I got. It's a bit difficult to explicitly tell the AI "pointing at a rock", and there's some distortion on the lamiamon due to the lora not knowing enough, but I think it's pretty good. Here are some personal images I made, two of which are from another lora I made that turned out a lot better. Also, yes, I like Morrigan, and I like succubi. Can't wait to be called Morrigananon lmao. Hmm... perhaps now that I have more flexiblity to explore AI, I should make a newer thread talking about recent developments and a better guide. The current guide is pretty outdated now. I could also try FLUX again but tbh I'm of the mind Illustrious is better for anime and NSFW.

>>26362 One of the images got cut off, I guess I'll also throw in an extra. Oh, and the lora is from one of Renetan's characters. You might know them from Tower of Alfimia or Princess Honey Trap.

>>26354 Understandable, based and tyvm!!

>>26354 How about black-tailed_prairie_dog_(kemono_friends) as herself, and hex_maniac as some kind of monster girl, in the previous wolfgirl Ruby poses?

>>26354 >that shit was impossssible hehe >As a consolation, have a nervous djiinn-lamia maid Breddy gud, I like her... I think I'll edit her colors a little to see if I can get closer to Lamiamon. >and some big titty oktoberfest elves Don't care much for those, but I noticed that I was thinking "eh, that's just some mid art" only later realized its all AI after all. These tools are really good nowadays. Like, that Lamia and 2 wolfgirl pics are easy to tell they're AI because of the high quality (few artists draw like that, and most AIs aim for something like that) and western looking, but the knife ears look genuinely jap.

>>26362 >So I figured I'd try to figure out how to train Illustrious loras. I've spent my afternoon setting that up, and decided to use your request as a test run. I got a somewhat functional lora of this character. >MF actually made a lora for this Awesome dude!!! How long did it took with that beefy 5090? >The quality isn't the best ever because there were less than 20 images in the dataset since this character basically doesn't exist. >basically doesn't exist I laughed at this line so hard, damn. I thought you were wrong about just 20 pics, but after going to gelbooru I stand corrected, there really is barely anything with her, probably even less useable for AI training. Please share the lora somewhere, since its already made, it'd be a shame if it went forgotten or unused. If its not too much to ask, can you try generating her again, just pointing slightly down at something and laughing? I think that'd be easier, and I can edit in the rock manually. And make the style a bit less shiny, maybe just simpler cell shading or something Again, thanks a lot, your awesome. Have some reaction pics as a reward.

>>26448 >>26354 Oh yeah, now it does look better

>>26448 >>26460 Yeah, The more anime looking one was the 4.5 version of NAI, which i don't like to use as it doesn't allow reference images ('vibe transfer') yet which means being consistent is near impossible. The 4.0 model does, which is the one i use for the watercolory images and why i can make nearly the exact same custom character over and over again. I've never messed much with Loras, but it feels like the same concept. 4.5 has some issues, but vibe transfer will solve them i think. + more random gens i've accumulated.

>>26467 >reference images ('vibe transfer') Wait, doesn't that mean you can just dump any image into it so that the AI bases the new gen on it? e.g. you throw it an existing Lamiamon fanart, tell it to do its thing, and it draws a new one? >The 4.0 model does, which is the one i use for the watercolory images and why i can make nearly the exact same custom character over and over again. Honestly drawing seems almost obsolete now, maybe like painting did when photography came around. I'll probably still draw every once in a while, but this is a game changer. Can you share links to what you use? Local or something online?

>>26471 >does it mean Yeah, it does. I use novelai dot net. However, it's not perfect and sometimes what you expect might not be what the ai takes from the image. There are sliders for reference strength and 'information extracted' so you just toy with those until you get a balance of what you want. Not monster girls, but here is an example of a collage of images i made with two characters repeating in various positions as a test. It's a maid trying to befriend/recruit an amazon. I generated multiple of each character and used imagerefs (as well as tags and stuff) to keep them as samey as possible throughout the different images and kind of tell a small story.

>>26471 But with custom characters that YOU did not make via tagging, like i did with these (your lamiamon example) it's extremely hard, just a ref image will not suffice. The ref image smooths out problems like variable clothing and hairstyles that sometimes crop up while keeping a distinct image style, mostly.

>>26480 So you make a character with tags, then? Do you reuse all the tags, and add the previous image as a reference? I want to learn how it all works

>>26495 I subscribe to it, but it's got some level of free usage. I would suggest goofin around and seeing what you can do. But yeah, like any model it uses positive/negative tags. I use tags to generate an initial character, and once i get a style i like, i save that as a reference for that character. Then, if i want to gen them in the same style as before, i load up the ref img and change the tags however i want for outfit / location / expression whatever

>>26497 I see, thanks >I subscribe to it, but it's got some level of free usage. I tried making some throwaway but I don't see any free trial. Maybe I'll throw few bucks their way, or just wait until I get something locally. Since you seem experienced with that site: does it do chan classics, like kkk hoods and alike? It's eula suggests its lame but who knows. I also want a powerful shitposting tool, which is why its relevant.

>>26500 i've never tried using it for that, per their site rules they dont track or store anything but who knows. I would imagine it works. It's very good with text with some help.

>>26452 Running on the maximum quality training settings- (Highest precision, best quality, using the most vram) It takes at most only an hour but seems functional at around 15-30 minutes. If I used a less intensive training configuration I could probably get loras within like 5 minutes (excluding the unavoidable time of collecting images, curating the dataset, tagging). I'd prefer having higher quality ones though. Here's the Lamiamon LORA. https://gofile.io/d/3eoj35 Gofile links expire after a while, so make sure to download it if you want it. I couldn't get it to zoom out enough from the Lamiamon to get a good picture you can edit, but I think I made the prompt a lot better. If you're curious about that, they're all embedded in the images.I got a bit fed up and started adding tags the ai definitely wasn't trained on like "pointing at rock" and it seems to have helped. Interestingly, it seemingly can implicitly understand advanced concepts in some cases if it knows the basic words, at least to some extent. And yeah, it was difficult to train the Lamiamon LORA. I'm honestly pleasantly surprised it turned out as well as it did, all things considered.

>>26533 not the requester, (i'm the NAI guy) but not gonna lie that did work out pretty well. It seems to not like the bonnet hat thing for most of them, but it's got a lot of the other oddity features down. Nice. Are custom loras easy to make? I was thinking i could potentially generate images of characters i made up using NAI and make my own loras to kind of expand my style capabilities.

>>26502 Text does look decent, I agree. Though I never really understood why that would be a "problem" for people, text is so easy to edit in manually. If I wanted manga, tshirts, or whatever else I'd just gen the core image and add the text manually. ... Thinking about the image, she looks more just retarded, not autistic. Autistic would be unfocused gaze, but not completely empty. When you look at this chick's eyes you see "head empty", an autist would look like "this head might be empty, or there might be something in there". More uncanny valley kinda look.

>>26533 >It takes at most only an hour but seems functional at around 15-30 minutes. Damn, I guess the newest, strongest GPU is really that good. Thanks for the gens and Lora. Do you plan training any other monster girl loras going forward?

>>26536 Not gonna lie the hat being missing is probably my fault. I trained the dataset to consider the clothes *separate* from the character, by tagging the clothes in the image so that the lora trained less on it. The bonnet would've appeared more consistently had I tagged it in my generation prompts. Similarly, I was getting red hair and white sclera until I forced it to be correct with my prompts. The winged arms were also missing until I tagged it. Custom loras being easy to make? Depends on your personal patience and autism level. I can probably make a dataset for one in at most an hour or two, but 15-30 minutes if I don't really care about scrutinizing the tags. After that, it depends on how good your GPU is. You could maybe pull by on an 11gb VRAM gpu and low quality LORA settings, but it would take several hours. These are generally the programs I use. LORA Training Reference Guide: https://rentry.co/qab9g Kohya SS GUI (Lets you train LORAs with a GUI interface and config options): https://github.com/bmaltais/kohya_ss Taggui (Lets you prune or batch add tags to images, remove duplicate tags, and auto-caption images reliably with something like waifu diffusion. You shouldn't rely on it fully, but it does most of the work): https://github.com/jhc13/taggui Imgbrd Grabber (This is a great one. Automatically harvests images from imageboards and you can configure it to generate caption files the training script uses, by downloading the imageboard tags for the image to a file. Which by default, are named like so (image1.png -> image1.txt): https://github.com/Bionus/imgbrd-grabber Just go to Tools -> Options Then inside, Save -> Filename, set tags separator to ", " Save -> Separate log files -Suffix without extension -Suffix .txt Text file content - %all% Side note about captioning- I've found the pruning strategy that works best is purging/deleting all tags you want the LORA to learn about your character, then making the *first tag* an ID for your character. Like "MonGirl, 1girl, whatever" You could then use MonGirl to tell the AI that you want to generate the lora subject. You can use some Taggui features to do that easily. Hope this helps if anyone actually wants to try training loras. I used to do this shit basically by hand so it's definitely far better than it used to be. >>26584 Maybe, I think it mostly depends on personal interest. I made a lot of LORAs privately for myself way back when, but I never posted them on Civit because I was worried people would call them shit lol. A lot of the LORAs I made back then have already been released by someone publicly though. Like, I made quite a few MGQ loras a while back. I think I'm better at making them than I used to be.