Voyeur handjob [Real]
Good thing you're hard, now jerk off for me π
Yes ma'am π
Training
160 steps on high noise
1 edited video (80 frames)
HLR + LCD (These acronyms were created solely to confuse you)
Lots of hope
Usage (Low noise)
This LoRA was trained only on High Noise, which means you'll have to use some Low Noise that knows what a penis is
(I used the Low Noise from DR34ML4Y v2).
Got an idea for LoRA? Then let's do it! (or at least try π€ )
In my repository, I created a model called "LoRA Requests", so if you want to request a LoRA, send videos and photos to help build the dataset for a public LoRA that will be posted here, that's the place to go.
Open LoRA Requests on HuggingFace π€
T2V:
The scene is in a public airport.
To the left, a woman is sitting in a pink chair. She is 25 years old, Latina, with long brown hair, long nails painted white, and is completely naked. She is curvy, her breasts are slightly sagging, and tan lines are visible on her breasts. She is looking at the man's hard penis.
To the right, a man is standing facing the woman. His face and chest are out of frame. He has fair skin, his body is average without muscles, his body has some hair. He is holding his own hard penis.
With his left hand, the man repeatedly moves his hand, stroking his own hard penis.
The woman looks at the man's face and smiles.You can change everything except the structure of the actions being executed
High Noise LoRA Scale: 1.0
Low Noise LoRA Scale: 1.0
Shift: 4
I2V:
As you know, Civitai moderators have to pretend they care about LoRAs that can remove clothing (Wan 2.2 without any LoRA can do this), and that's why I won't post an I2V prompt or example. But in my repository on HuggingFace, you'll find the LoRAs not published here, all uncensored, with examples and everything.
About HLR + LCD
This is a fast-learning technique, which makes LoRA less flexible. This can drastically reduce creativity, but it yields stable results while using few resources.
Negative effects:
It will probably only work at the same camera angle
High chance of not responding to different prompts
High chance of forcing the original characters of the training video
Training only the High Noise reduces this chance, but it can force things that are VERY similar, like the same hair length, same color, etc.
Low Noise
Help me creating more
If you want to help me continue making LoRAs, or if you want me to make a LoRA for you, buy 5000 PlayCoins at Aisha-AI and transfer them to my account (account number 2).
This helps Aisha-AI to stay alive and produce new LoRAs for you all π
About Buzz β‘
I've been getting a lot of buzz since I started publishing the LoRAs, but it's not very useful. It just makes you spend money. So thanks for the donations, but please don't send buzz.
If you want to help, buy PlayCoins, that really helps me keep making more LoRAs.
Description
First version