Also that he was basically given the job of doing an impression of another actor doing a character rather than being able to do something unique. Joel Kinnaman has an intensity that seems like it would be very hard to imitate.

I could see a system where you very loosely define a handful of keyframes, give it some kind of description for what your looking for, and then the model fills in the rest for you. It almost certainly would still require some tweaking on the artists part, but I think a huge benefit is that AI can be non-deterministic. If you don’t like what you got you can just run it again without changing inputs. Maybe save multiple runs and manually combine all the best elements. Lots of opportunity.

Most digital animation done by hand isn’t done in the stop motion/frame-by-frame way, It’s done with key frames that are interpolated between. That’s not to say it isn’t still super time consuming (especially when done well).

I’m the same way, if I don’t talk out loud or write my ideas down I can’t think straight. Without an inner monologue my thoughts just feel like a jumbled abstract soup I have to manually untangle by speaking. I also get songs stuck in my head, but I’ve always explained it as feeling a particular part of the rhythm, or almost feeling the lyrics in my mouth like I’m speaking them.