All my models are FREE, and all I ask is for your support by following, thumbing up and bookmarking! Thank you!
VERSION 2.0 IS NOW AVAILABLE WITH THE FOLLOWING REVISIONS:
Vulva/vagina is MASSIVELY improved, looking proper and correct now
Tongue is improved, looking proper and correct now
Improved consistency
Added more poses
1,000+ additional training images
HIGHLY RECOMMEND TO UPGRADE IF YOU HAVE VERSION 1.0!
Requires LyCORIS support (not an issue if your GUI is up to date).
Compatible with SD 1.5 checkpoints only.
More sample images are available at: https://civarchive.com/posts/6491777
Introducing an all-in-one (i.e. "Ultimate") LORA for heterosexual cunnilingus! This LORA envelops virtually every position possible (standing, sitting, lying, close-ups, facing away, facesitting) with the only exception being POV. Trained on the largest database for cunnilingus (over 3,000+ high quality images), I want this to be every cunnilingus lover's ultimate creation tool.
This is however still in active development. There will be a lot of ironing out consistency and compatibility issues in future updates, so please be in acceptance that this is still just a TOOL and NOT a SOLUTION.
This is a highly advisable alternative to my Ultimate Cunnilingus Concept for Photorealism (Heterosexual) LORA. This will work significantly better on anime and 2.5D styled checkpoints. It additionally works with photorealism, but in comparison to the photorealism LORA, photorealism comes out much smoother and softer (which some people may prefer).
This is still a bit experimental. While it can produce good results a lot of the times, there are still a few issues to be resolved⎯mainly compatibility with various anime checkpoints (see recommended checkpoints below).
Note: If you are only interested in generating photorealistic or photorealistic anime cunnilingus, I suggest you try the photorealism version first. It works on almost all checkpoints (including pretty much all anime ones). If you don't like the results (e.g. the photorealism is too intense), you can then try this version.
Available here: https://civarchive.com/models/405949
Recommended Checkpoints:
For photorealism:
Most NSFW photorealism checkpoints will work fine. Currently, I like epiCPhotoGasm (epinikion), t3 (darksagaq12926), AsianRealistic_SDLife_Chiasedamme (Hoang_StablediffusionLife), majicmixrealistic (by Merjic), Dreamshaper (Lykon). Using full 1 weight is usually no issues with these checkpoints.
Important: Use DPM 2M++ sampling method (automatic scheduler type) for photorealism!
For anime:
Cheemsborgar Diffusion Chevre Soft by cheemsai
Copax 2D Anime by Copax
Mothmix by bombasticmori
Incursio's Meme Diffusion by FallenIncursio
zodiac hentaihub by zodiac444
AniToon by Samael1976
MasterAnime by Masterjp123
HelloFlatAnime by aji1
DuelAceWaifuMix-2.5D by noesca
Fantasticmix25D by michin
Fantexi_v0.9Beta by zhazhahui345
PornMaster-Anime by iamddtla
richyrichMix by richyrich515
Sweet-mix by Manseo
Sudachi by Ikena
SDHK by hakoniwa
Dark Sushi Mix by Aitasai
Anime Soft by XRYC
The Neuro-Evolution by boristheblade911
The WonderMix by Lorim
Model-EX by Nico53425342
Goofball Mix by Goofy_Ai
FiaMix Reboot by Fia_TKTD
Kawaii Realistic Manga by szxex
Important: Use Euler a sampling method (automatic scheduler type) for anime!
Anime checkpoints that currently do not work and just generates garbage (will need to be looked into):
AbyssOrangeMix2 - Hardcore by Havoc (use photorealism version instead for now)
Any vanilla NAI (NovelAI) checkpoints, which includes Animefull and some versions of Anything. Why would you want to use these for generation, anyway?
Anything that isn't listed is up for your experimentation. I'm also currently testing more SD 1.5 checkpoints and will continue to update this list.
Remember to always either use ADetailer or img2img inpainting for female faces (see ADetailer section)!
Usage:
No unique trigger word is necessary, but you should follow the example prompt for consistent and best results.
Weight of 0.7-1 is recommended. If faces are distorted or looks weird, it can be easily fixed with ADetailer (see ADetailer section) or img2img inpainting. Lower weights will allow the checkpoint more expressive freedom in generating cunnilingus, but higher weights will generate more consistent results.
Sampling method: Euler a for anime and DPM++ 2M for photorealism. Automatic scheduler for both.
CFG scale should be 5-7.5. I find that 5-7.5 gives the best quality yet still follows the prompt very precisely. There isn't really a need to go above 7.5 in my experience. There is a big risk of introducing artifacts at higher CFG scale.
Stick with default SD 1.5 base resolutions! 512 x 512 (square), 512 x 768 (portrait) and 768 x 512 (landscape). You can probably do okay with 768 x 768 (square), 640 x 960 (portrait) and 960 x 640 (landscape). Higher resolutions will cause weird issues such as multiple heads, limbs, etc. If you wish to go higher, please use HiRes fix or img2img upscaling!
Use at least 30 sampling steps!
Use clip skip 1 or 2. I just stick to 1 and it seems to work fine, although some people swear anime works best with 2.
Make sure you use an appropriate VAE. I use this one.
Example Prompt:
Most Basic Prompt:
1girl, 1boy, hetero, (((cunnilingus, boy licking girl's vagina, boy licking girl's pussy, best quality, masterpiece))), nude, open mouth, closed eyesYou should always add more specifics however as it can result in less weird and randomness, such as setting, breast size, hair color, clothing parts, etc. Remove "nude" if adding any clothing parts!
Note: girl and boy can be exchanged with woman and man (e.g. 1woman, 1man, man licking woman's vagina, man licking woman's pussy). This can help to prevent appearance being too young. Putting "underage" as a negative additionally helps.
Optional tags that may provide more varied results:
hand on another's head, spread legs, ass, anilingus, sitting on face, full body, from above, from below, from front, from side, open mouth, closed eyes, tongue, tongue out, oral, pubic hair, pussy cum, pussy juiceNegative:
ugly, bad quality, low quality, worst qualityYou should also absolutely use this general negative prompt which seems to improve image quality drastically (literally a night and day difference):
watermark, text, censored, deformed, bad anatomy, disfigured, poorly drawn face, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, disconnected head, malformed hands, long neck, mutated hands and fingers, bad hands, missing fingers, mutation, poorly drawn, huge calf, bad hands, fused hand, missing hand, disappearing arms, disappearing thigh, disappearing calf, disappearing legs, missing fingers, fused fingers, abnormal eye proportion, abnormal hands, abnormal legs, abnormal feet, abnormal fingersGeneration:
It may take a few attempts at generation to get a good result. Semi-good results can be salvaged with img2img generation or inpainting. As with any concept LORA, playing with RNG is a part of the game (usually with the player losing awfully). If you do not get good results or the checkpoint is not generating cunnilingus, keep trying! If after about 10 generations (considering your prompt follows the example + using the correct sampling method) and nothing is turning out right, definitely use a different checkpoint (refer to the recommended checkpoints list above).
Detail Tweaker is RECOMMENDED!
To add even more details, I highly recommend combining this LORA with Detail Tweaker. I usually use a weight of 0.5 to 1, depending on how sharp and detailed I want the image to be.
ADetailer is HIGHLY ADVISED!
Using ADetailer with detection model confidence threshold of 0.83 will almost always exclusively detect the female face and fix it, making it look much better. Males usually do not need to be fixed, and fixing them with ADetailer can cause them to look messed up (that's why a high detection rate is necessary).
Make sure to additionally put this into the ADetailer prompt:
1girl, cunnilingus, detailed faces, best quality, masterpieceDo NOT put this LORA in the ADetailer prompt for best quality!
For photorealism, use inpaint denoising strength of 0.4-0.5. For anime, use 0.5-0.6.
When the faces looks too realistic for anime, it can be easily fixed with the above!
Alternatively, you can also fix the faces later in img2img inpainting (using the same ADetailer prompt above). ADetailer however is just a lot quicker with less steps.
Can I use this for yuri/lesbian cunnilingus?
You can try, but I have not attempted this nor do any of the trained images are of yuri/lesbian. If this does not work well, there are other existing yuri/lesbian cunnilingus LORAs that already do this and to a good extent. However, in future versions I will additionally include support for yuri/lesbian cunnilingus.
Can I use this in combination with other LORAs like characters?
Yes, but be careful with using too high of a weight on the character LORA or too many LORAs at the same time. I recommend one character LORA only with weight of 0.7-0.8 (on the character LORA).
Is there any POV cunnilingus?
Not at the moment. I'm not a big fan of POV style and there are already plenty of POV cunnilingus LORAs available. If you want POV added, let me know and I can try adding it on future versions. However, adding POV will make it more difficult to generate non-POV images, despite correctly tagging with triggers (as exemplified with the many universal cunnilingus LORAs available). Therefore, a separate POV only cunnilingus LORA may be necessary.
Can I choose the specific position of cunnilingus to generate (e.g. standing, sitting, lying, etc.)?
Not yet precisely, as this requires separate trigger tags for every position and is very difficult and time consuming to implement (perhaps in future versions?). You can however try adding position tags and see if it helps, but there is no guarantee SD will follow it. At the moment, it's best to be vague about position and let SD roll the dice so you can get the most unique results.
The results look REALLY BAD or I'm not getting cunnilingus!
First, make sure you are following the example prompt exactly. Second, make sure you are using the correct sampling method (Euler a for anime and DPM++ 2M for photorealism). Afterwards, if you're not getting cunnilingus, just keep trying to generate and you'll likely get something as it can take a few generation attempts (this is just due to the current nature of SD 1.5 not really understanding the concept very well).
If after about 10 generations and you're still not getting cunnilingus or just bad results, it's probably an incompatible checkpoint. Some checkpoints (most notably non-NSFW ones) do not work well with this LORA or at all, unfortunately. It's not possible to make sure it looks and works well on every possible checkpoint, so please try a different checkpoint. Again, please check the recommended checkpoints list for recommended ones to use.
You can also try lowering the weight if it's simply an issue of image quality.
Check back often for updates!
This is a serious project for me and I will be updating, fixing and improving this LORA as often as possible, including adding new training data for even more delicious cunnilingus. So please bookmark and check back often for new updates!
Feedback welcomed!
I'd love to hear you feedback and ways I can improve this LORA. Sharing with others is caring, and is the only way I have the motivation to release and update LORAs for free!
Description
Initial release.