upload image -> describe motion -> get video

Enter fullscreen mode

Exit fullscreen mode

That description hides the real problem. A single still contains only one view of a subject. When we ask a model for a fast camera orbit, a full-body walk, or expressive gestures, we are asking it to invent information that was never present in the source.

That is where identity drift, unstable lighting, texture flicker, and waxy faces come from.