Mise-en-Video adds 3D staging control for multi-shot video
Training uses a 160,000-video set with hierarchical multi-shot text and oriented 3D bounding boxes.
3 stories, newest first · one card per story
Training uses a 160,000-video set with hierarchical multi-shot text and oriented 3D bounding boxes.
StoryEngine tracks explicit story-world state so multi-shot video stays narratively and visually consistent.
MovieGrid arranges long videos on spatial grids during post-training, generating 6.05x more shots than temporal packing with state-of-the-art cross-shot consistency.
Today 1.6K readers · 2.4K views · 774 reads · all time 189K views