EDIT: 9/30/23 The only limit is really is the consistency over time but that we think is solvable, but with enough controlnet refinement anything is pretty much possible. you just have to use controlnets to guide towards what you want, and loosen them as you go. I definitely recommend using this despite it being trained on some nsfw content, as you can see above, its very easy to prompt negative nsfw to avoid any of it, I'm just trying to be transparent on its origins. I'll still leave it marked for intended for mature themes.
EXPANDING ON CONTROLNETS: you need them for the motion you see in my top examples, basically what the value is here is that its easy to maintain consistency in the reality around the characters, unlike base mm14, and even mm15v2
A couple different Models I have attempted to train have led me to a couple results that people seem to be interested in, though I'd still say this is an unsolved science, but there seems to be a noticeable change in the way they interact with general motion but also the style of trained data. they aren't perfect, at least I don't think so, they are still trained on incredibly small datasets
OH I SHOULD INCLUDE THIS, it doesn't have to be anime, its motion, you just choose what model you want, I just happen to use it for this model and lora, but its trained on actual porn so, its not just limited to this character.
OH AND DOUBLE ALSO: the motion is really good because I am using animatediff-cli-travel-prompt with controlnets for assistance, whats notable about this model is the stability of the image for a longer duration than normal motion model v14. but if you put in the work I'm not sure what its limit is and what it isn't capable of doing.
Maybe I'll make a tutorial for tomorrow to share. Support isn't required but appreciated :3
Description
I'M CHANGING THE NAME FOR A REASON:
basically, this model is just really good in general, I definitely like using this model most of the time and just shows a better ability to be animate in general. What I'm trying to say is while it is training on nsfw material, the motion model doesn't have that much power over the normal tokens of stable diffusion, so if you simply put nsfw in the negatives, and are using controlnets you're highly unlikely to get nsfw out of it. its pretty safe to use and with another patience, you can chisel out anything you want.
Consider sponsoring it, I'd like to devote all of my time to developing this tech and I could really use some support :D
as stated before, try them out, tell me what you think, this was trained on IRL nsfw videos.
This one is not like the anime model, I'm just putting all most intriguing models into one post so its not spammed.