Wan 2.2 I2V Creampie LoRA - Cr34mp13
My first attempt at training a Wan 2.2 Image-to-Video (I2V) LoRA, showing promising results for NSFW workflows. I haven't had much change to test it properly so post away!
Note: Trained High Noise Lora to 80 Epochs and seems to have gotten rid of the liquid coming out of the mouth issue, currently training Low Noise and will update it when it is done.
Overview
This LoRA is designed to be used in the second part of a full NSFW workflow for merging two videos - one video starts the NSFW act, and this LoRA helps with the finishing/creampie effect. The main objective of the Lora was fora strong Creampie effect during penetration. Seems to work for Anal and Oral Creampie as well. Further testing is required.
Strength: 0.6 - 1.0
Training Details
- Dataset: 79 clips (2-8 seconds each)
- Resolution: 320 x 192
- Content Mix: 70% realistic + 30% anime
- Anime addition helps with exaggerated action and fluid amount
Prompts
Vaginal Creampie
cr34mp13, Thick white cum is pouring out of her vagina and around the penis. Lots of thick transparent white cum flows out as the penis goes in and out of her vagina.
Anal Creampie
cr34mp13, Thick white cum is pouring out of her asshole and ass around the penis. Lots of thick transparent white cum flows out as the penis goes in and out of her ass.
Notes
- All examples done with LightxV2 Speedups
Support
If you like what I'm producing and would like to support me and help me make more awesome Wan 2.2 I2V Lora's, a coffee can go a long way :). Also will do custom requests, just hit me up.
Thanks!
Description
FAQ
Comments (8)
epic cool, works like a charm if you combine two loras, the main animation one and this one at the end. ( as default style one for image generation)
any way we can get seperate models for oral creampie and vaginal, many times the vaginal creampies i prompt result in the person throwing up cum
for cowgirl or missionary, It's still easy to confuse between mouse and vagina, doggy style work great, Nevertheless, thank you for your model
Not sure if this will help anyone else, but shorter videos seem to be more consistent.
For me, 5 seconds (81 frames) of I2V had cum leaking from a random place, usually the mouth.
And 2 seconds (45 frames) of I2V had it come from only the ass every time, which is exactly what I prompted.
I ended up making four 45 frame videos and sticking them all together.
Seems like the training data might need reworking for more consistent 5-second videos?
cant get proper realistic color... its always way too white almost cartoonishly too white
That was largely the point as it was trained for the exaggerated anime style. Sorry not sure if a more realistic colour can be achieved with this Lora
Can you do the same, but exclude oral entirely from the dataset? It's poisoning vaginal/anal by adding cum leaking from mouth
It is said that SD1.5 can't even distinguish between "vagina", "anus" and "mouth".
It will only draw "semen / liquid" on the most prominent, central and prominent hole on the human body - that is, the mouth.