DragNUWA
DragNUWA is a video generation model that utilizes text, images, and trajectory as three essential control factors to facilitate highly controllable video generation.
微软研究院博客
加载中…
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.