Experimental proof of concept for lesbian sex with strap-on dildos. Created at the request of a user. Final checkpoint 24 epochs ~5220 steps. Still hit or miss videos. Trigger word is 'str4p0n'. Other words used in training ' 2girls, nude, black harness, strap-on, sex toy, dildo, object insertion, vaginal insertion, vaginal object insertion, anal object insertion, two topless women engaged in a sexual act. breasts, pussy, yuri, vaginal, sex toy'. Use at your own risk.
NOTE: while the content is present. it is very prompt and seed dependent. i'm not very proficient at prompting this style of content. so, i'll keep posting anything that turns out semi-indicative of training clips.
v2.0 changed workflow, 27x3sec clips 256x256 resolution, added some hair pulling and close-up clips to spice up the generation, blurred faces for better lora interaction, 24 epochs 5228 steps.
v1.0 seems a little better. Still not impressed. Maybe i can't prompt for this content... I may redo it with not so verbose captions? Let me know if anyone gets anything nice...
Sample videos can be saved and dragged into comfyui to see prompts and workflow examples. YMMV.
I used this process for local training:
https://civarchive.com/articles/9798/training-a-lora-for-hunyuan-video-on-windows
46x2 sec video clips sampled at 430x430 resolution.
Description
new process - 27x3 sec clips, 3 models, 24 epochs, 5200 steps, added new clips of close-up dildo penetration to spice things up.
FAQ
Comments (11)
No matter what I do with lora settings, always resulting the Monroe girl looking... although she is a hot dancer
are you using my breast massage lora or exotic dancer also? monroe was not used in this lora... only exotic dancer and breast massage. exotic dancer 2.0 was retrained with more models and blurred faces. i'm in the process of retraining breast massage 2.0 with similar settings. i see what you mean though. she is one of my favorites. maybe she's contaminated my computer...
nice videos by the way. i looked through them. only a few look close to monroe, but it's not her. version 2.0 had blurred faces, so it's hunyuan choosing. unless training could depixel the blur..
very strange. the 5th video you posted has exactly monroe belly dancer video hair, earrings, face, breasts... that's too much of a coincidence. are you sure you're not using one of the other loras i mentioned? i did some testing, i can change hair, skin color, breast size, but it seems only major face changes are if i prompt for asians. any other nationality while not exact, are similar face structures. skin color had to go to 0.5 lora strength to change. ghost in the machine...
I don’t suppose you’d be interested in making this for Wan2.1
It's on the list
I downloaded your example video , and I have to tell you you have the most pointless workflow , 90 percent of it is useless I can not believe you use such a bs workflow , it matches this non working Lora
couldn't get it to work either. and that workflow made my eyes glaze over
sorry, new to comfyui. cutting and pasting pieces of workflows together. you should have just needed settings, not the workflow... sorry it didn't meet your expectations...
none of your sample(or gallery images) prompts match the model. they're all for the bellydancer lora
Yeah I got tired of loading vids to get prompts to all my videos. Can you save the vi id and drop it in comfy.