How far away are we from "type in a prompt, get an animation" generative style UX?
What are some roadblocks of making that a reality?
What are some roadblocks of making that a reality?
From some anecdotal experience, large language models struggle with spatial structure (which makes sense given their modality and training data). On the other hand, diffusion models create great images, but this does not translate very well to vector data.
Animation is not a very well researched modality for AI, so it could go either way. It's definitely an interesting direction to consider, as it can democratize motion design even further.
https://www.youtube.com/watch?v=CgKNTAjQpkk
You'd have to convert to vector, or tweak your model architecture to work with vector format.
Once that issue is fixed, then it's a green light as everything else is vaguely ready.