I gave it my best shot. I'm sure another iteration or two would make it better. Dataset of 71, superhero comics, and mostly Superman at that.
I tried to teach it the difference between arm and hand poses.
Arm poses: Arm_up, arm_down (can be combined) arm_back (like flexing with the other arm up) arms_up, arms_down, arms_behind, arms_out
hand poses: clenched_hand, clenched_hands, flat_hands, open_hands
Oh and legs_together of course!
I hope you like it :)
Description
FAQ
Comments (5)
Seems a bit... inconsistent. Some things it will do fine (which is more than I've gotten from tags alone), but others its all over the place.
Tell me what I should be focusing on?
@Gwenwithgreeneyes I'm not really sure where the problem lays. It seems very angle specific with what will and won't work, and will randomly bend the back and legs.
I added a bunch of pictures, showing what can go wrong (and some that went right) but they won't show up if X and XXX visibility are enabled.
@NanashiAnon Best results seem to come when ticking all the boxes, but even then...well, I'll have to put some more work into it :/
Honestly,IL isn’t capable of understanding this pose yet.