All samples are t2v generations and 100% fake. Check my profile for additional samples. This lora is not for the undressing of real people.

If you like my "work" please consider tipping my electricity bill: https://ko-fi.com/loralai8256

BTC: bc1qce69wlzt7mdw2q0rfj0afqrd3m73070yrg3uav

Upcoming loras: general purpose futanari/cowgirl (check my videos for a preview of that) and a really good realistic cumshot lora (both for Wan 2.2 I2V) which are coming along very nicely. In final testing stages.

This is a lora for frontal shots of a big white cock in flaccid and erect form, there is no trigger word. The flaccid shots are better but the erect cock and masturbation concept works, it just might be require a little more seed hunting for the best shot. Side angles also work but I haven't tested any kind of overhead or POV shots.

Please check the sample videos I posted for some ideas of prompting. It's quite flexible, the most important words for the penis controls are:

"erect standing penis"
"penis hanging down"
"flaccid penis"
"penis sticking straight out from her/his shorts/skirt/pants/jeans"
"her penis twitches/sways/bounces"
"she pulls down her shorts and her penis springs free" (if this causes too much penis bouncing, try "penis springs free and hangs down" etc, or just follow my example prompts and hunt for a good seed)

This lora works very well with character loras as there are no faces in the training data, so it should play nicely with them. It's not just for women/futanari, it should work absolutely fine for male characters too.

Recommended settings:

Without speedup lora (I use 20-30 steps usually):

20 steps

Euler/Uni_pc/dpmpp_2m (I usually use Euler)

Beta scheduler

CFG 3.5-5.0 for high/low models

9 steps on high noise, 11 steps on low noise with shift 5

11 steps on high noise, 9 steps on low noise with shift 8

Lightx2v works pretty well with the low noise model, I do NOT recommend using the lightning lora for the high noise model. The police officer, sunglasses, bathhouse and library futanari samples were with the low noise lora applied.

With speedup lora:

20 steps

Euler/Uni_pc/dpmpp_2m (I usually use Euler)

Beta scheduler

CFG 3.5-5.0 for high noise, 1.0 for low noise model

9 steps on high noise, 11 steps on low noise with shift 5

11 steps on high noise, 9 steps on low noise with shift 8

When using the speedup lora you can probably use less steps than 20 but that worked quite well for me, the problem with the speedup lora is it can mess up with the shape of the penis, so beware.

Training information:

Rank 16, alpha 8, discrete flow shift 3.0 for high noise training, 1.0 for low noise training

Cosine with restarts, 2 cycles, 1e-4 learning rate,

20 images, 768x768, 5 clips at 200-240p each 3-5 seconds,

3700 steps for high noise, 4000 for low noise (overkill, I could have used less steps for sure)

Upscale information:

I use Davinci Resolve to interpolate to 30fps and use its AI Super Scale for a bit of added clarity, I prefer this to using upscale models and RIFE in Comfy.