LLM-grounded Video Diffusion Models

Text-conditioned diffusion models have emerged as a promising tool for neural video generation. However, current models still struggle with intricate spatiotemporal prompts and often generate restricted or incorrect motion. To address these limitations, we introduce LLM-grounded Video Diffusion (LVD...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Lian, Long, Shi, Baifeng, Yala, Adam, Darrell, Trevor, Li, Boyi
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!