Accelerating Text-to-Video Generation with Calibrated Sparse Attention
Open paper
Benchmark
Model
Rank
Results
text-to-video-generation-on-vbench
CalibAtt (Wan 2.1 14B, 480p)
–
VBench Total Score: 80.4
VBench Quality Score: 82.3
Rank counts only results with a code link.