Please consider buying my two albums Sisters of the Wicked and Danger Ahead, my book Dracula and also please check out my YouTube channel. Civitai won't support creators, so any purchase is a real help. Thanks.
DRACULA https://www.amazon.com/dp/B0FM4DXYPL
Sisters of the Wicked https://amazon.com/music/player/albums/B0DSJY3ZHY?marketplaceId=ATVPDKIKX0DER&musicTerritory=US&ref=dm_sh_CdyeuxIBNBDOjZ1hpB1PPJxT0
Danger Ahead https://www.amazon.com/music/player/albums/B0DB2DV354
Music In The Machine https://www.youtube.com/@musicinthemachine/videos
Acorn Is Boning XL V3
V3 came about after I had been away from SDXL for probably close to a year. I was working with a company trying to make realistic characters for use in online chat avatars that were NSFW. They were using Lustify. In working with it, I found it to have some good qualities, but not very good prompt adherence. I decided to go back to my original Acorn Is Boning XL as the base for a new model. V1 didn't look quite as realistic as V2, but it had better prompt adherence, so I used block merging to graft on the better visual look of Lustify onto the better composition and prompt adherence of Acorn Is Boning XL. I made a few versions for testing and found two of them to be very good and fairly similar. Here I posted version 3.0 and posted v3.1 for online generation over at Tensor.Art. https://tensor.art/models/860244001473710239/Acorn-Is-Boning-XL3-3.1
You can try it out over there if you like and compare.
Acorn Is Boning XL V2
https://www.youtube.com/@musicinthemachine/videos
I would appreciate a follow and any comments or any posted results of images. Thanks.
For V2 I was able to improve the photorealism as well as the consistency of better hands.
Like with my primary model, Acorn Is Spinning XL V4, I changed my default generation resolution to 1024 X 1328. I think this change was part of the reason for the hand improvement as I get improvement in my previous models at that resolution as well.
I get tired of all the same old porn poses so in this initial gallery, I have included a mix of regular poses along with some img2img stuff and some fantasy themed porn. If you are trying to reproduce my images and can't, it's probably one of the img2img pics. Enjoy!!
My go to sampler is still DPM++ 2M SDE Heun Exponential, typically either 30 or 60 steps with CFGs from 2 to 7, more often 2 to 3.5.
Acorn Is Boning XL
This is the first SDXL version of my Acorn Is Boning model. If you enjoy it, please follow me. I enjoy working on models and hope to keep doing it. Getting in the Creator's Program is based on followers so far so I need all I can get. It is much appreciated.
https://www.youtube.com/@musicinthemachine/videos
I use some of my models for videos on my YouTube page if you want to check it out.
As with my previous 1.5 versions, I made a randomizer prompt that takes advantage of dynamic prompts. You can set the seed to randomize and run off batches. Go back to tweak those than stand out to you. Enjoy.
highest quality photograph of beautiful naked woman {(vaginal sex:1.5) with man, erection | (from above, BLOWJOB, big cock) | (manually masturbating:1.3) with (blue glass dildo insertion:1.3) | (kneeling), (receives cum in open mouth from man's cock:1.4) | (squatting, peeing piss:1.4) | (licking penis, cum:1.4) | (giving deep throat blowjob:1.4) | (having sex with another woman:1.4), (manual dildo inserted:1.5) | (POV BLOWJOB:1.4) | (having anal sex:1.4) | (kneeling masturbation, touching own pussy:1.4)} {in the bathroom | in hot tub | in the kitchen | by the pool | in bedroom | on rooftop in the city}, {ginger | blonde | brunette} {long | medium | short} hair, {petite | skinny | chubby} body, {(large breasts:1.3) | (medium breasts:1.3) | (small breasts:1.3) | (huge breasts:1.3)}, (intricately detailed skin), (perfect lips), 18 years old, high contrast
Negative: (watermark:1.5), (anime, eye contact, misaligned:1.4), (missing limbs:1.5), (blurry), (deformed iris), (deformed legs) (extra feet, extra hands), (lipstick), (two dicks)
DPM++ 2M SDE Heun Exponential is my preferred sampler but many work just fine.
I prefer to use 40 steps or more, but you can get good results at lower steps as well, at least down to 20.
CFGs from 3 to 9 all work pretty well.
Description
FAQ
Comments (49)
I dont know why this checkpoint doesnt show up in the model searches. I had to use a link to see it. I see all the other SDXL nsfw checkpoints on the search.
I don't know. I just typed Acorn in the search and it comes up right away as the second item after my Acorn Is Spinning model.
+1 I came across this one randomly it doesn't show up in normal searches for nsfw
hey bro, could you please upload this to tensor.art? awesome work!
I have linked it to Tensor Art. I think it takes a while to update there. My AcornXL V2 model is on there, so hopefully it will show up soon.
Thank You for Your Great Sharing! great model!
My pleasure. Glad you like it.
I think, its best porn model today.
Thanks. I think so too for now. :)
This is a perty good model. Thanks!
This is now my go to model for porn, amazing job.
Thanks a lot.
Best porn model I have seen and it's actually really good on non porn as well. Not as good as the main Acorn XL2 model, but very nice.
If you can beat the elongated body, it will be an absolute hit!
Really, I haven't had any problems with elongated bodies in general.
this problem exists across many SDXL checkpoints but I've mostly solved it with the phrase "Marfan syndrome" at the beginning of my standardized negative prompt. I've also had some success with "tall" and "elongated torso" and "stretched subject" in the negative, but "Marfan syndrome" is the only one that made it into my every-image-I-generate negative prompt.
@shapeshifter83 I have really only got elongated bodies occasionally when using one LoRa that didn't come out very well.
Maybe a very basic question, but how can I use this model? I really don't know, where can I find tutorial for adding this one? No clue. : )
I'm not sure what you mean, at least now without a little more info. If you mean using it on the CitivAI site, I don't believe they currently have the XL models in the generator. If you mean using it on your own computer, then all you do is download it and put it in your "models" folder in whatever webui you use to generate images. I use ForgeUI mostly and have it installed on my second hard drive, the "D" drive, so for me the folder is D:\Forge-webui\stable-diffusion-webui-forge\models\Stable-diffusion.
@Seeker70 thanks! I'm new to the club. Discovering everything.
This checkpoint finally convinced me to switch to SDXL. Great work. What models did you merge to create it?
Thanks for the comment. Sorry, I have been away a couple of weeks. Had to have heart surgery.
Anyway, the base for the model was my own Acorn XL V2. I experimented with super merger to mix in one of the newer porn models. Trying to keep the realism of mine while combining the poses from the other. If I am remembering correctly, the porn model I used was OnlyForNsfw118, which is a very nice model as well. I just think mine is the best photo model available so I wanted to try to bring my level of photo realism to this model type. Most of the porn type models are pretty cartoony for my taste. I'm glad you enjoy my work.
this model is capable of greatness I never thought possible. Thank you
Thanks for the compliment.
Absolute awesome model!
Thanks a lot.
This model is so good! Any info if there will be an updated version?
Thanks. No info currently as far as updates. I recently had a heart surgery and am still recuperating. Also since it is a merge made starting with my own Acorn Is Spinning XL V2 as the base, there really would need be some new better model of the porn type available to be able to make any upgrade to it. Right now I think this is the best porn type model available and I haven't noticed any newer or better ones yet.
@Seeker70 I think you should take a look at this. https://civitai.com/models/502468
@nsleptsov18954 I looked it over. Most everything in the gallery looks very fake. I might download it and try it, but based on current evidence, it doesn't look too promising. We'll see after I try it.
@Seeker70 in image to image that model realy good at understanding of b/g poses. the best I've seen so far. just need to tinker with the settings.
I am looking into an update, but it's pretty hard to improve on it. I have a few candidate versions that I'm testing. We'll see.
@Seeker70 An upgrade could be great! I have lot of weird body (3 arms or legs). Do you think a merge with another photorealist model could help ?
@Psykokwak I am not sure if that would help specifically with extra arms or legs as I haven't seen much for models where that doesn't occur. For me it is mostly about prompting. I don't get them much because prompts like "(extra leg:1.5), (extra arm:1.5)" are regular parts of my basic negatives. I am working on a potential update, but I have made about 7 or 8 candidate models and testing is pretty time consuming. A few of them are definitely promising, so we'll see how it goes.
@Seeker70 Great! Let me know if I can help.
@Seeker70 first of all I really hope you recovered after the surgery! I totally missed out on yorur response, sorry! Your new tests sound amazing, very nice to see that you're still experimenting :) all the best and can't wait for an update.
@pornthulhu Thanks. Recovery has been ok. Almost back to normal now. I have pretty much only been working on Flux since it came out. I don't see a lot of potential yet for an Acorn is Boning Flux. There are a few Lora models that add a little, but I haven't seen much evidence so far that they can all be combined to create an overall model that can do everything. So far, the best I do normally is create images with Acorn is Boning XL and then use img2img to upgrade them with Flux.
This is really fucking great. I can't say enough nice things. This is the model that really got me motivated to get back to the grind of dataset cultivation. I know the work that goes into this level of quality. I don't know how big your dataset is, but i've got 10k well cropped, denoised, and resized images currently. Let me know if you'd like to do an equivalent exchange. Rising tide raises all ships.
Thanks for the compliment. I don't have any datasets though. I don't have a machine good enough for training models. My skills lie in recognizing things in other models that can improve mine and and using the merging tools to get those things into my own. This model was achieved by starting with my own Acorn XL 2 photo model and merging with a porn model so I could get the ability to get the porn-like poses with much more of the photo realism of my own model. It did come out quite nice and if you use it for non-porn, it's actually still a pretty darn good model.
@Seeker70 well, you've certainly got a very well balanced set of weights. Would you mind if I did some finetuning and loras based on this? Full attribution, of course.
@gurilagardnr Feel free. I am always happy to see what people do with the stuff. I always try to make sure all the generation info is showing on my stuff too for those who want to try to reproduce images. Although lately they might have trouble. I leave the info in, but I have been playing quite a bit lately with image2image so the prompts don't always get the same outputs.
I'm fairly novice when it comes to creating AI art and I've struggled so far, but finding this model changed everything. Fantastic.
I am glad you having a good experience with it. Welcome.
Great model! Any tips for fine tuning?
My main suggestion is if your computer is capable, generate at the highest resolution you can rather than low res with hiresfix. I usually generate at 1024X1280 at least, and lately I have increased it to 1024X1328 most of the time. Lately I have been using my Acorn Is Spinning XL3 model a lot more, but my XL2 model was the base I used to make this model, so they work fairly similarly. Oh, and I never ever go without Adetailer if a face will be in the image.
@Seeker70 awesome thanks! Has anyone successfully made a LORA or a new checkpoint off this model yet? I'm trying to fine tune it now on a subject using the AdamW optimizer, having trouble getting the learning rate dialed in so far.
@devnuller2002 I couldn't say for sure. I don't do much with Loras. I have made a few, but I have never had much luck when using anything but the original SDXL base model for Loras, but again, I rarely use Loras as my goal is to make the models not to need Loras.
@devnuller2002 I have made many loras, lycoris, and dora's from acorn is boning. I have not released any publicly, but it works very well as a model to train against for nsfw poses and anatomy. It's likely in my top 2 for that.
@gurilagardnr That's cool. I guess if I make any more in the future I should try using my own model. I just make Loras so rarely and the few I have tried using anything other than the original base model came out awful. Again, for me, my goal is aways to improve the model so that Loras are not needed, so I only have a few character ones myself. I have used a few other Loras lately though. There is one I use that puts a crowd in the background of scenes that I have been using with Acorn Is Spinning lately and it gives good results.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



















