List your company

Text-to-Video Generation on VBench (Quality and Efficiency Metrics)

77.17VBench Semantic ScoreCalibAtt
73.0174.0975.1776.25Mar 5, 2026

Evaluation results

MethodLinks
CalibAttResolution=480p, Num Frames=81, Sampling Steps=4, Backbone=LightX2V2026.0377.1782.2981.2670.911.21.29—
RadialAttentionResolution=480p, Num Frames=81, Sampling Steps=4, Backbone=LightX2V2026.0377.0282.4681.3748.412.71.14—
SpargeAttentionResolution=480p, Num Frames=81, Sampling Steps=4, Backbone=LightX2V2026.0376.482.0880.9449.613.51.07—
SVG2Resolution=480p, Num Frames=81, Sampling Steps=4, Backbone=LightX2V2026.0376.1982.6481.3562.7240.6—
Dense (FA3)Resolution=480p, Num Frames=81, Sampling Steps=4, Backbone=LightX2V2026.0376.0682.2881.04014.51—
CalibAttResolution=720p, Num Frames=81, Sampling Steps=4, Backbone=LightX2V2026.0374.0478.877.8473.930.61.57—
SpargeAttentionResolution=720p, Num Frames=81, Sampling Steps=4, Backbone=LightX2V2026.0373.4778.7577.6949.939.91.21—
RadialAttentionResolution=720p, Num Frames=81, Sampling Steps=4, Backbone=LightX2V2026.0373.2478.6877.652.5371.3—
SVG2Resolution=720p, Num Frames=81, Sampling Steps=4, Backbone=LightX2V2026.0373.1978.8377.761.947.31.02—
Dense (FA3)Resolution=720p, Num Frames=81, Sampling Steps=4, Backbone=LightX2V2026.0373.1778.7477.63048.31—
50% stepsMACs (T)=21.933, Speedup=1.86×, Sampling steps=20, Base model=Wan2.1-1.3B2026.04——————43.14
DiffSparseMACs (T)=18.124, Speedup=2.05×, Sampling steps=20, Base model=Wan2.1-1.3B2026.04——————43.83
DuCaMACs (T)=20.332, Speedup=1.69×, Sampling steps=20, Base model=Wan2.1-1.3B, Sparsity ratio (R)=54%2026.04——————43.56
DuCaMACs (T)=18.124, Speedup=1.68×, Sampling steps=20, Base model=Wan2.1-1.3B, Sparsity ratio (R)=59%2026.04——————43.3
Lumos-1Params=1.5B, Time (8×A100 GPU-Days)=85.42025.07——————78.17
Open-Sora Plan v1.2Params=2.7B + 13B, Time (8×A100 GPU-Days)=> 5922025.07——————75.98
Wan 2.1 - 1.3BMACs (T)=43.866, Speedup=1.00×, Sampling steps=20, Base model=Wan2.1-1.3B2026.04——————43.82