This new paper from Alibaba is called MIMO: Controllable Character Video Synthesis withSpatial Decomposed Modeling<p><a href="https://menyifang.github.io/projects/MIMO/index.html" rel="nofollow">https://menyifang.github.io/projects/MIMO/index.html</a>
credit: <a href="https://x.com/alexcarliera/status/1838962098111737901" rel="nofollow">https://x.com/alexcarliera/status/1838962098111737901</a>