General Information:
This was trained on natural language, not tags. It will work best if you use full sentences to describe what you want.
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 (anal and vaginal)
hand in panties
handjob
hitachi magic wand
implied blowjob
ipcam / nightvision ipcam
masturbating (might want to put penis in negative prompt, or specify what she's rubbing for women)
massage
missionary position
naked, nude, etc.
penis
pregnant (and can specify trimester)
prone position
reverse cowgirl position
sex
sheer
snapchat (and caption/text/etc)
selfie (and mirror selfie)
spooning position
strap-on dildo
tentacles
licking testicles
undressing
vagina
wet clothes
Description
FAQ
Comments (3)
So far, KR2 has been a struggle in many ways, particularly due to its basic training. One of its major flaws is its marked preference for anal penetration over vaginal penetration, even without prompting for anal. Some might appreciate this, but for me, a good model is one that doesn't force anything and follows the prompt. To solve this problem with KR2, I had to use a specific LoRA, SNOFS. It works well. So my question is simple: is your LoRA capable of consistently render vaginal penetration?
Is this related to the SNOFS model?
The naming is nearly identical and your description also is almost identical to the SNOFS model.
Edit: I just compared the descriptions and your description is 1 to 1 identical to the v1 SNOFS description...
Edit2: Your file size is 1.46 GBs also... Like this seems either like you completely copied the SNOFS lora or you used it as a training base, but it seems pretty BM to do so without referencing the original Lora what so ever.
I've read the description and tried the model, however this lora is doing nothing. Characters remain clothed, no action takes place. SNOF works fine as does realisim engine. Using krea-2-turbo-fp8 or krea-2-turbo-bf16 model to test with this. I've tried with and without the filter bypass. Am I missing something or does this lora only work with unlocked diffusion models?
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.