PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference
Open paper
Benchmark
Model
Rank
Results
text-to-video-generation-on-vbench
Wan-DMD (4 steps)
–
VBench Total Score: 83.33
text-to-video-generation-on-vbench-2-0
Wan-DMD (4 steps)
–
VBench-2.0 Total Score: 57.48
Rank counts only results with a code link.