Ultimate Cunnilingus Concept for Photorealism (Heterosexual)
Details
Download Files
About this version
Model description
All my models are FREE, and all I ask is for your support by following, thumbing up and bookmarking! Thank you!
VERSION 3.0 IS NOW AVAILABLE WITH THE FOLLOWING REVISIONS:
Significantly improved consistency
Improved image quality
Improved faces
Fixed skin tones
Prompt emphasis "(" and ")" are no longer necessary
Reduce necessity for negatives, and now works well with just a few negatives such as "ugly, bad quality, low quality, worst quality"
HIGHLY RECOMMEND TO UPGRADE IF YOU HAVE A LOWER VERSION!
Requires LyCORIS support (not a problem if your GUI is up to date).
Compatible with SD 1.5 checkpoints only.
More sample images are available at:
https://civitai.com/posts/12117639
https://civitai.com/posts/12155123
https://civitai.com/posts/12400468
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.
Update: An anime/photorealism mix version of this LORA is now available and offers a balance of the two. It is recommended to try this LORA as well as the anime/photorealism mix version, as both LORAs produce very different style results. One or the other may suit your tastes better. Available at: /model/424879
Usage:
No unique trigger word is necessary, but you should follow the example prompts for consistent and best results.
Weight of 0.7-1 is recommended (0.8 being the sweet spot). If the weight is too high, faces can become distorted (using ADetailer can help - see below). Lower weights will allow the checkpoint more expressive freedom in generating cunnilingus, but higher weights will generate more consistent results.
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 if you can. 512 x 512 (square), 512 x 768 (portrait) and 768 x 512 (landscape). You can probably also 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!
Sampling method: DPM++ 2M for photorealism and Euler a for anime. Automatic scheduler for both.
Use at least 30 sampling steps!
Use clip skip 1 or 2. Some people use 2 for anime/2.5D checkpoints, but I just stick to 1 all the time and it works well.
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
You 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, ass, anilingus, spread legs, sitting on face, clothes lift, full body, from above, from below, from front, from side, open mouth, closed eyes, tongue, tongue out, oral, pubic hair, pussy juice, pussy cum
Negative:
ugly, bad quality, low quality, worst quality
If you need additional negatives, this is the one I often use. Note that using this changes the image quality drastically, so please experiment!
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 fingers
Generation:
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. You can look at my example images for the checkpoints I use and recommend.
Detail Tweaker is RECOMMENDED!
To add even more details and photorealism, 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, masterpiece
Do NOT put this LORA in the ADetailer prompt for best quality!
Use inpaint denoising strength of 0.4-0.6.
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 anime checkpoints?
Yes, this LORA can generate pretty great results with a lot of anime checkpoints! However, this was not intended to be used for anime and therefore will add a heavy layer of photorealism, which may not be your intended expectation. However, if you like more photorealism in your anime, then this should work very well in that regard! Using a lower weight (such as 0.7) can help bring back more of the anime style. You can see some anime checkpoints that I transformed into more photorealistic anime in my example images (and they look quite good imo).
You can also try the anime/photorealism mix version of this LORA available here: /model/424879
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 may 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 (DPM++ 2M for photorealism and Euler a for anime). 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 my example images for recommended checkpoints 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!