This is my newest and most revolutionary version of this lora. I realized most of these lora's focused on one particular angle like pov, from the side, from the front and thought why can't one lora do them all? So here you go, version 3 of my lora.
The relevant keywords are "under view", "side view", "frontal view", and "pov" and of course doggystyle. They each control the preferred angle of the output.
"Side view" is the traditional view from the past versions.
"frontal view" is from a forward angle. Not directly head on, at a slight angle but with the woman facing almost directly towards you.
"pov" is exactly what it says. A direct pov shot.
"under view" shows you from behind and under so you get full penetration view with full dick and balls in view. The only problem is that because Wan struggles with genitals you sometimes get weird genitals but they can be improved by adding a second lora that focuses on genitals.
Example prompts are:
an under view of a woman with red hair being fucked doggystyle as she faces towards the left. Her ass is in the air with her vagina visible as a man with a large black penis begins thrusting, his penis visible as it slides in and out of her. She is bent over a desk and they are in an office setting.
A side view of a woman with pink hair and pale skin being fucked doggystyle as she faces towards the right. She is positioned with her face on the ground and her ass in the air with her hand on her ass as a large white man is positioned behind her thrusting into her with his large penis visible as it slides into her. They are on a beach and she is face-down in the sand.
A frontal view of an african woman with green hair and dark skin being fucked doggystyle as she faces towards the right. She is laying flat on her stomach as a large asian man is thrusting against her, his large penis visible as it slides in and out of her. They are on a public sidewalk in a busy city with onlookers watching.
A frontal view of an Asian woman with black hair being fucked doggystyle as she faces towards the left. She is on her knees, with both her arms held behind her with her chest pushed out so her breasts jiggle and sway beneath her, Behind her an asian man is holding her arms as he thrusts against her. They are on the moon with the earth visible in the background.
A pov of a woman with brown hair and white skin being fucked doggystyle. There is a red strap going across her back, and her ass is aimed towards the viewer. Her anus and vagina are visible, and a large white penis is sliding in and out of her vagina as she pushes her body back and forth against it.
You can prompt facing left or right to pick which way the woman is facing as well. I trained it on realistic videos, but you can use i2v to use it for anime or whatever else.
Description
This is the neThis is the newest version with more added to my dataset provided by logenninefingers888. I didn't realize until I uploaded them that if you don't specify the direction the women face to the right but you can specify other directions.
Some example prompts are as follows. This is the prompt for the first video:
"a side-angle view of a man and woman having doggystyle sex. They are standing in a public restroom, and the woman is bent over wearing an open flannel shirt with her breasts hanging out and she is nude from the waist down. The man is also nude from the waist down with his shirt pulled up. He is holding her waist with both hands and thrusting into her as her large breasts jiggle."
The second video with the rainbow hair is:
"A realistic overhead side-angle view of a woman with light-colored skin, long rainbow-colored hair and large breasts bent over the hood of a car as she is fucked doggystyle. Her breasts are swinging wildly as the man thrusts his hips against her, causing her entire body and breasts to jiggle. The man is only visible from the shoulders down, and both his hands are gripping her waist as he penetrates her from behind. A crowd of people are standing in the background holding up cellphones that occasionally flash as they take photographs."
You can specify the angle like behind, overhead side views. and above to get different angles. Behind will usually have the woman facing away, and above will have her facing you but at a side-frontal.west version with more added to my dataset provided by logenninefingers888. I didn't realize until I uploaded them that if you don't specify the direction the women face to the right but you can specify other directions.
FAQ
Comments (20)
v2 works well with t2v, nice
Thanks, if you notice anything that looks bad let me know so I can correct in the next version.
@asdrabael seems to work well so far, definitely a big upgrade. maybe it's a skill issue on my behalf but sometimes the guy just thrusts his hips into the air or he sometime he doesn't have a dick.
@crombobular
I think that's Wan not knowing what a dick is. There's stuff I need to change, like the captioning a little and of course more data. I found some small issues, like it will sometimes make an weird cgi hybrid output, or the dudes dick will look weird and misshapen.
This is great. Can you add a prompt example? Thx!
I'll add prompts later today hopefully. I rushed it out this morning as I was leaving for work.
Teamwork makes the dream work :)
You guys are doing god's work. Thank you
Is trigger for V2 actually "doggystyleE"? With two "e"s?
No, that's a typo. Thanks for pointing it out so I can fix it
What's a good weight for Anime/Cartoons?
That I couldn't tell you because I tested exclusively with realistic. It can do a little CGI but there was no animated clips in the training data.
Use i2v. At least you're sure that you start a long generation with a good image. And the rest will be generated with Wan with the same style. You can always add (I'm doing it, can't say yet if it really makes any different) animated cartoon in positives, and realistic / realism, in negatives.
But yeah: I2V. Just use that.
@SD_AI_2025 Is V2 not I2V?
@Devilday666 I2V is the Wan Model you use. Wan Loras trained with I2V model work only with the I2V model, whereas the Loras trained with T2V model work with both, at least in most cases so far.
Also what's the difference between yours and logenninefingers888
Bigger datasets. Me and him traded our respective datasets with captions.
We also aimed for different things. His aimed for more visible penetration and the ability to do anal. Mine aimed more for jiggle physics. I wanted extreme flapping of breasts and ass. I combined our datasets plus added more data i was gathering but wasn't clipped or captioned yet to get both. Since he has my data he possibly could put out a differently trained lora.
Thanks for the training. Although a copy-paste of your samples' prompts would have been kind of nice.
They're coming. I meant to do it yesterday but didn't have time. Hoping I can today
@asdrabael Thanks ;)