Brutal Dildo
The field where I am writing this right now has a label, simply "Description*". The label also has a description... you know, that little line of text below a title or label. The description for Description reads:" Tell us what your model does"...
Well... I'd really rather not, but you know what they say! A picture says a thousand words, and videos, I assume, are at least as wordy... so just look at the showcase, okay?
If you download one of the showcase videos and drag it over ComfyUI, you'll get the prompt and a workflow.
Versions
front
All front view, mostly low angle, 5e-5, 256x256 and 432x240 for 50 frames. This one delivers brutally. Try "notched, scaly, horse, tentacle" with various bases. No back views trained at all. Works very well and seems very flexible. The lower resolution might be hurting things like hands though...
back
I finished training this a couple days ago but my tests were not delivering the results I was hoping for. Multiple concepts are harder for LORAs to hone in on and this run didn't impress.
However, this version does the back view very well, while front does front views better, so if that's what you're going for, you can probably skip back. It is what it is...
Three
Because I found that back will place the dildo in front of the woman and not always inside. and not a single one of my videos was not 100% focused on the penetration, clearly something went wrong.
I studied the concepts and dived deep into the subtle effects captioning and prompting provide to this process. I learned even more about captioning, including some very non-intuitive things, all detailed at length in my training guide. I think the fruits of my labour and patience with training a multi-concept LORA have paid off, or maybe my prompts are just better...
Alas, I can confidently say that third time's a charm, and this is the best one yet in my tests.
4.2.0
Zeroing in on optimal captioning strategies, this run does the trick nicely with much better faces. Enjoy!
Prompting Tips
HunyuanVideo tends to require more than just a trigger word. Prompt explicitly what you want to be seeing, using unambiguous phrases that align with the action you expect. My LORAs are trained for flexibility which means just adding the LORA into the workflow and using the trigger word is not going to take over and force you into it's world.
What my LORAs do is gently but convincingly guide HunyuanVideo to reproduce the action and basic poses associated with this concept. If you find that something is not hitting quite right, my suggestion is to really spell it out, and if that's not enough, straight up describe what you DON'T want to see.
Training
My training techniques are discussed at length here.
I've uploaded the full training set and configuration files for reference only. The videos are all publicly available, but who knows what's actually allowed, so tread respectfully and carefully please. Alas if anyone has a problem with this I will take them down immediately.
Disclaimer:
Run