notesum.ai

Published at December 10

Mobile Video Diffusion

cs.CV

cs.AI

Released Date: December 10, 2024

Authors: Haitam Ben Yahia¹, Denis Korzhenkov¹, Ioannis Lelekas¹, Amir Ghodrati¹, Amirhossein Habibian¹

Aff.: ¹Qualcomm AI Research

Arxiv: http://arxiv.org/pdf/2412.07583v1

Refer to caption

Model	NFE	FVD $\downarrow$	TFLOPs $\downarrow$	Latency (ms) $\downarrow$
Model	NFE	FVD $\downarrow$	TFLOPs $\downarrow$	GPU	Phone
Resolution $\mathit{1024\times 576}$
SVD	50	$149$	45.43	376	OOM
AnimateLCM^∗	8	$281$	45.43	376	OOM
UFOGen^∗	1	$1917$	45.43	376	OOM
LADD^∗	1	$1894$	45.43	376	OOM
SF-V^∗	1	$181$	45.43	376	OOM
Resolution $\mathit{512\times 256}$
SVD	50	476	8.60	82	OOM
MobileVD (ours)	1	171	4.34	45	1780