This model is trained on a dataset composed almost entirely of real-world photography. The primary goal was to achieve realistic textures and lighting, moving away from the "plastic" look common in purely synthetic datasets. While the model is an ongoing project, it performs reliably for its intended purpose.
This version is based on Krea 2, which produces highly stylistic results. It works well with weights set to 1 and handles uncensored content effectively. (Note: I apologize for the delay with this release, as I was quite slow to publish a LoRA that had already been on my computer for nearly a month).
✨ Key Features & Usage
No Hard Trigger Word: You generally do not need a specific trigger word. If you want to emphasize size, adding keywords like "huge" or "big" will prompt the model accordingly.
Body Type Adjustments: Training on real-world data often biases models toward generating curvier body types. This model attempts to maintain a balanced default; however, if you prefer a…
A clothed version of my other macromastia LoRA. This one here cannot produce X or XXX reliably.
The model is pretty straight forward. Use the trigger early in your prompt. Further descriptions to the breasts position, framing and focus can help a lot to emphasize the effect.
Sometimes it creates thicker or chubby bodies, for that you can include descriptors like slim or skinny or use negative prompts.
Values over 1.0 may produce heavy artifacts. Decrease strength if you encounter artifacts. Most samples use a strength of 0.9.
For more, have a look at the example images/videos.
trigger words mcrmst gigantic breasts
Upload snofsSexNudesAndOtherFunStuff_v14Distilled__fp8.safetensors with huggingface_hub
Flux 2 Klein 9b V1.4:
Additional training. Some of the training was done using https://github.com/BuffaloBuffaloBuffaloBuffalo/ai-toolkit-perceptual , training against depth. Considering how much of SNOFS is two people intermingled with close skin colors, it seemed like a novel idea. It did seem to rapidly help with that sort of thing. On the downside, it seemed to create a bit of a texture issue on very close up images. I did some more training after to try to bring that back and was somewhat successful, but I think I'd need to increase the weight decay to really make that happen. Since everything else was in a good state I decided to release as-is. If you do have that texture issue, try adding "goosebumps" as a negative prompt.
Flux 2 Klein 9b V1.2:
More training - anal still doesn't work super reliably. Added images with terms like 'condom-wrapped penis,' 'boudoir' and 'anilingus' (again, doesn't work super great yet).
https://civitai.red/models/1972981/sex-nudes-other-fun-stuff-snofs?modelVersionId=3104629
Krea 2 V1.1:
More training, should go along way toward Krea 2's propensity for anime and digital art stuff.
I created two custom nodes to help with the two stage workflow that make it really easy, and also easy to customize for towards your preferences. The images of v1.1 have the workflow attached, but you can also find the nodes and a workflow here:
https://github.com/Auryg/Krea-2-Two-Stage-Sampler
Use the trigger mcrmst and describe the breast/cleavage in some detail. Use the WAN 2.1 VAE for more realistic outcomes. Use the filter bypass LoRA for better results.
Training model: Krea 2 Turbo + Training Adapter
LoRA strength: 0.5-1.3
Sampler: euler / euler a
Steps: 8+
VAE: WAN 2.1
mcrmst, A photograph of a woman with gigantic breasts, her voluminous, heavy breasts dramatically stretching and filling the soft beige cable-knit turtleneck sweater, creating deep curves and visible fabric tension despite the modest high neckline, sitting on a picnic blanket in a serene autumn forest.
Use the trigger mcrmst and describe the breast/cleavage in some detail. Use the WAN 2.1 VAE for more realistic outcomes. Use the filter bypass LoRA for better results.
Training model: Krea 2 Turbo + Training Adapter
LoRA strength: 0.5-1.0
Sampler: euler / euler a / euler+beta57
Steps: 8+
VAE: WAN 2.1
mcrmst, A photograph of a woman with gigantic breasts lying on her side on a bed, her massive, round chest prominently displayed. She has long, wavy blonde hair and looks directly at the viewer with a calm expression. The background features a dimly lit bedroom.
Version Comparison
Krea_V1 is trained on high-qulality SFW and NSFW 4K images so it can handle both. Besides making images more detailed it also reduces asian face bias. Note: For simple nsfw use nsfw words in prompt, for hardcore stuff use other loras with it.
V4 is trained on more refined and 40% nsfw dataset, so besides better quality it has NSFW detailing capabilities too. Note: This is only for detailing, for simple nsfw use nsfw words in prompt, for hardcore stuff use other loras with it.
V3 is trained on professional 4K quality images with higher steps. It applies very subtle skin texture which looks more realistic, without producing freckles and burnes.
V2 for more natural looking skin texture than V1, can produce freckles and moles for some time. It is good at preserving skin tone and lighting also.
V1 tends to produce overdone skin texture like more pores and freckles, and it can change lighting and skin tone also.
🖼️ Generation Settings
Weight: 0.6-0.8
Krea_V1 Trigg…
I trained this model using a dataset composed almost entirely of real-world photography. My goal was to achieve realistic textures and lighting, moving away from the "plastic" look of purely synthetic datasets. While this implies the model isn't technically "perfect" yet, it does a crazy good job at what it was designed for.
✨ Key Features & Usage:
No Hard Trigger Word: You generally don't need a specific trigger word to get results. However, if you want to emphasize the size, simply adding keywords like huge or big will push the model to the limit.
No Body Type Bias: Almost anytime traning a model like this using real data, most of the models should have a natural tendency to generate "chunky" or curvy women, this model besides shouldn't do it. If it does and you prefer a slimmer physique, simply add skinny to your prompt, and it should correct the body type without issues.
Wardrobe Malfunctions: Be aware: if your prompt includes "cleavage," the model has a high probability of gen…
Presenting DR34MSC4PE's WAN LoRA:
DR34MJOB - Single and Double Blowjobs (POV+)! It, as a nice surprise, is excellent at handjobs too!
Please remember to like and share - if you like our work, give us a shout below!
===========================================================================
9/20 - Come and get it... WAN 2.2 I2V updates are here!
Note: You need BOTH models to produce good output. If you don't like what you see - adjust the CFG!! We hope you enjoy. =)
===========================================================================
Sample Prompts:
d0ubl3_bj, A close-up view of two women performing a double blowjob on a man's erect penis. The woman on the left has light brown skin blonde slutty pigtail hair. Her nails are manicured with a glittery design as she grasps the base of the penis. The other woman has light tan-lined skin and skin black hair with bows and her eyes are closed. Both women are focused on the man's penis which is circumcised and erect. They both lic…
This LoRA is made for use with Z-Image Turbo and focuses on generating realistic, curvy women with a PAWG body type — thick thighs, big hips, and natural proportions. It keeps the vibe photorealistic without going over the top, and works great for anyone who wants fast, high-quality results without messing with a bunch of settings.
You’ll get smooth skin, clean body shapes, and solid consistency across different poses. Just plug it into your Z-Image Turbo workflow and prompt it like usual — no need to overthink it.
Good at:
✔ Realistic thick body types
✔ Smooth shading, believable curves
✔ Fast results with good quality
The model is pretty straight forward. Use the trigger macromastia early in your prompt. Further descriptions to the breasts position, framing and focus can help a lot to emphasize the effect.
Sometimes it creates thicker or chubby bodies, for that you can include descriptors like slim or skinny or use negative prompts.
Values over 1.0 may produce heavy artifacts. Decrease strength if you encounter artifacts. Most samples use a strength of 0.9.
For more have a look at the example images/videos.
LTXV 2.3 - V1
Coming in late May...
WAN 2.2 T2V - V1
After using the trigger macromastia, use additional triggers large, huge and gigantic to control the size further, see example video. Can be combined with Thiccification.
Training model: WAN 2.2 T2V
LoRA strength: 0.3-1.0
Sampler: euler / euler a
Use TripleKSampler with 1/4/4 steps or no lightning LoRAs at all for quality.
Use breast physics LoRAs to improve jiggle and motion for very large breasts. I highly recommend Huge Natural Bre…
A clothed version of my other macromastia LoRA. This one here cannot produce X or XXX on its own and honestly most R would be considered PG-13.
The model is pretty straight forward. Use the trigger macromastia early in your prompt. Further descriptions to the breasts position, framing and focus can help a lot to emphasize the effect.
Sometimes it creates thicker or chubby bodies, for that you can include descriptors like slim or skinny or use negative prompts.
Values over 1.0 may produce heavy artifacts. Decrease strength if you encounter artifacts. Most samples use a strength of 0.9.
For more have a look at the example images/videos.
LTXV 2.3 - V1
Coming in May...
WAN 2.2 T2V - V1
After using the trigger macromastia, use additional triggers large, huge and gigantic to control the size further, see example video. Can be combined with Thiccification.
Training model: WAN 2.2 T2V
LoRA strength: 0.3-1.0
Sampler: euler / euler a
Use TripleKSampler with 1/4/4 steps or no lightning …
A LoRA to create (very) thick female bodies. This model cannot produce X or XXX on its own and honestly most R would be considered PG-13.
The model is pretty straight forward. Use the trigger thicc early in your prompt. Further descriptions to the body, hips, thighs, framing and focus can help a lot to emphasize the effect.
Values over 1.0 may produce heavy artifacts. Decrease strength if you encounter artifacts. Most samples use a strength of 0.9. Can be combined with Macromastia (Clothed) or even the naked version.
For more have a look at the example images/videos.
LTXV 2.3 - V1
Coming early May...
WAN 2.2 T2V - V1
I mainly use this to improve the results of Thiccification but it can be used solo.
Training model: WAN 2.2 T2V
LoRA strength: 0.3-1.0
Sampler: euler / euler a
Use TripleKSampler with 1/4/4 steps or no lightning LoRAs at all for quality.
Use thigh/butt physics LoRAs to improve jiggle and motion.
A thicc plus-sized woman standing in a bathroom, wearing a sweater,…
From https://civitai.red/models/2227622?modelVersionId=2545249
trigger words
sfb3hind, sfbehind
This lora is focused on intimate moments captured from front facing camera ideal for subjects facing the camera in doggystyle, plow, prone, or ¾ front positions, it can work from the side but no recommended. This LoRA's aim is to create accurate dynamic movement, as well more facial expressions:
Keywords, phrases:
→ Short thrusts, fast thrusts, slides in and out, penetrates
→ Fast, slow, rough
→ Pulls her hair, hands on neck
Workflow:
Here is a quickly organized and noted WF video. Save it and drag it into Comfy UI. https://civitai.com/posts/25545461
Initial images:
For the V2.1: Starting images are a mixture of Z-image base checkpoint, and Pony CyberRealistic V15.0. Then I add do some enhancements with Zimage, Qwen, Qwen-edit to make them pop a little more.
The dark 'Raw' styled images are z-image and a style lora I'm working on.
https://civitai.red/models/1972981/sex-nudes-other-fun-stuff-snofs
SNOFS was trained on natural language, not tags. It will work best if you use full sentences to describe what you want.
Want to support my work or help fund the training of this dataset on other models? Join the Patreon in my profile, and if you do - thank you!
Not using ComfyUI/your inference software doesn't support lokr? I've put up a merged version here: https://civitai.com/models/2416142?modelVersionId=2716480
By the way, if anyone out there needs an expert in fine tuning text-to-image models (especially one that's also a software engineer), reach out to me. I'm currently looking for employment.
Here's a list of some of the terms that work well:
anus
blowjob
boudoir
condoms
deepthroat
braless
cowgirl position
cum
cunnilingus (be specific and maybe put kissing in the negative prompt)
deepthroat
dildo
doggystyle position
fingering
hand in panties
handjob
hitachi magic wand
implied blowjob
ipcam…
uploading from https://civitai.red/models/1428098?modelVersionId=2156435
https://civitai.red/models/1428098?modelVersionId=2156435
r3v3rs3_c0wg1rl, a nude woman with light brown hair small breasts and a navel piercing straddling a nude man with a visible erect penis penetrating her vagina. The man's hands grip her hips from below as she rides him in the reverse cowgirl position facing forward with a slight devilish smile. His penis is thrusting into her and his testicles are visible below. They are in an urban street setting at night with neon signs in the background including a prominent red and blue "NEON" sign. Cars are parked along the street and buildings with lit windows line the background. The perspective is from a low angle looking up at the woman. The lighting is bright highlighting their bodies against the dimly lit street. The woman's legs are spread wide and the man is lying on his back beneath her.
c0wg1rl, a nude woman with light skin long blonde hair and small breasts straddling a man who is lying on his back. The woman's legs are spread wi…
I trained this model using a dataset composed almost entirely of real-world photography. My goal was to achieve realistic textures and lighting, moving away from the "plastic" look of purely synthetic datasets. While this implies the model isn't technically "perfect" yet, it does a crazy good job at what it was designed for.
✨ Key Features & Usage:
No Hard Trigger Word: You generally don't need a specific trigger word to get results. However, if you want to emphasize the size, simply adding keywords like huge or big will push the model to the limit.
No Body Type Bias: Almost anytime traning a model like this using real data, most of the models should have a natural tendency to generate "chunky" or curvy women, this model besides shouldn't do it. If it does and you prefer a slimmer physique, simply add skinny to your prompt, and it should correct the body type without issues.
Wardrobe Malfunctions: Be aware: if your prompt includes "cleavage," the model has a high probability of gen…
Example T2V prompt:
At the beginning of the video, a m4crom4sti4 overweight fatty black woman with oiled and shinny skin is in the distance outdoors at golden hour. She has dark mahogany hair with red undertones ponytail, and (oversized macromastia breasts). She is fully nude, totally naked model showing natural skin texture. She stretches seductively while breaking eye contact with the camera. Her macromastia breasts jiggle with each movement. As the scene progresses, she spins around with a confident expression. She tilts her head at the camera. She maintains eye contact with a shy expression while playing with her nipples. In the final part of the video, the camera does a sharp zoom-in close-up on the woman's cleavage as she moans softly. The bakground is silky canopy bed.
This LoRA, incredibly, manages to handle ALL of our specialty LoRA concepts (Double/Single Blowjobs, Missionary, Reverse Cowgirl, Doggy), wrapped in one model! It obeys very well and is largely extremely accurate to the given keyword/position (see samples below)! Don't be shy; give it a try! =)
===========================================================================
3/7 - DR34ML4Y LTX! (w/Sound) is HERE! -- This is a tech preview. It will work for both LTX2 and 2.3. Please note - read the model description and understand that the trigger words STILL WORK but your surrounding prompts will need to be much more verbose in the style LTX2 requires! It is also likely best used in non-super huge resolutions, until retraining is complete specifically for 2.3's increased latent space.
EXAMPLE WORKFLOWS HERE! Shout out to RuneXX!
AS ALWAYS: Enjoy, generate responsibly and share what prompting tricks you learn along the way!
================================================================…