LightVAE: Towards Compact and Efficient Video Autoencoders
Open paper
Benchmark
Model
Rank
Results
text-to-video-generation-on-vbench-2-0
LightVAE-Lite (MiniMax-H3)
#1
VBench-2.0 Total Score: 66.5546
VBench-2.0 Physics Score: 75.3712
…
Rank counts only results with a code link.