Now with prompt engineering, we can do text-to-image and text-to-video.   Now, how about text(description)-to-mesh, text(description)-to-shape, text(description)-to-scene, or even text(description)-to-world?<div dir="auto"><br></div><div dir="auto">Can semantics help this?</div><div dir="auto"><br></div><div dir="auto">John</div>