Search papers, labs, and topics across Lattice.
Applied Artificial Intelligence Initiative, Deakin University, Australia 2 FPT Smart Cloud, Vietnam 3 Deakin University, Australia 1,3 {minh.le, duc.nguyen, truyen.tran}@deakin.edu.au 2 kiendd6@fpt.com Abstract High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of spatio-temporal tokens which can be modeled using Diffusion Transformers (DiTs). However, this approach faces a trade-off between the strong but expensive Full
1
0
3
FrameDiT achieves state-of-the-art video generation by ditching token-level attention for a novel matrix-based attention that operates directly on entire frames.
