They sit, we tie, it's all in good fun!
We've seen lying, standing and even hanging out. Let's take a break and just sit for a while. How long? Well these subjects will be there until you untie them!
I present... drum roll
Tied Sitting
~8 full body videos, ~6 ones including the Hitachi magic wand (reproduced with limited success) and a bunch of close ups to teach the right details, this training run is worth the post. I may add more videos and retrain this at some point to try to improve the details, but until then, enjoy the one, the only, the... One.
add the second trigger term "v1bed" and a phrase "holding the h1tach1 magic wand vibrator to her vagina" for the secondary concept.
Delays
I dived so deep into training over the last few weeks that I've gotten a bit jaded. I kept aiming for the perfect LORA and I think at some point I got too picky and kept throwing away training runs that weren't 'perfect'. I let perfection become the enemy of progress and while I did improve quality, I could have released a few of these weeks ago. I have to remind myself now that:
No LORA hits perfectly on every seed...
All LORAs will occasionally render something messed up....
But when I'd see something I didn't like, I'd just trash it and start over, and when starting over implies a 16 hour training run, lots of time goes by in between.
Future Direction
I have a dream now, of training on my entire BDSM training sets, expanding to various positions, restraint types, settings, clothing, etc... some sort of BDSM Uber LORA. I think that my footage and captioning skills are where they need to be, but it's likely that I'll need to run a very low learning rate for 2-3x as long as I usually do to get something stable. Meanwhile, I'm going back through the footage I set aside looking for more good clips to bonify the datasets; this will take lots of time and captioning needs to be accurate and strategic for results to be good, so I can't rush this at all.
I may eventually attempt some of the other concepts people have suggested (sex positions++), but many of these already exist and I'm less keen on producing more of the same.
There are many other BDSM concepts that I'd like to train, but finding high quality footage of clear and focused examples of the more obscure ones is difficult at best.
I also may eventually train for WAN, but I don't use that model and the time it will take to prep and run those trainings will cost me lots of time and energy, ultimately for LORAs I won't personally use at all, so we'll see. *What I am open to is sharing my datasets. I'm not the possessive/selfish type at all. The only thing is that I have spent tens of hours collecting and captioning these sets, so I reserve the right to be be selective about who I share stuff with.