DragNUWA
DragNUWA is a video generation model that utilizes text, images, and trajectory as three essential control factors to facilitate highly controllable video generation.
Microsoft Research blog
Loading…
Microsoft Research Blog
Research Focus: Week of September 25, 2023
Chunked prefills & decode-maximal batching boost LLM inference; DragNUWA combines text, image, and trajectory for fine-grained video content control; reconstructing images from human brain signals; structural inequalities in creator-audience relationships.