Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-Video Generation Inference on T2V Models HunyuanVideo, Wan2.2
Loading...
199
Latency (ms)
RoME
-1,397.84
9,380.83
20,159.5
30,938.17
Apr 10, 2026
Latency (ms)
Speedup (%)
Updated 5d ago
Evaluation Results
Method
Method
Links
Latency (ms)
Speedup (%)
RoME
Model=Wan2.2, Paramete...
2026.04
199
3.9
RoPE
Model=Wan2.2, Paramete...
2026.04
209
-
RoME
Model=Wan2.2, Paramete...
2026.04
759
3.4
RoPE
Model=Wan2.2, Paramete...
2026.04
790
-
RoME
Model=Wan2.2, Paramete...
2026.04
1,120
4.3
RoPE
Model=Wan2.2, Paramete...
2026.04
1,170
-
RoME
Model=Wan2.2, Paramete...
2026.04
4,350
3.3
RoPE
Model=Wan2.2, Paramete...
2026.04
4,500
-
RoME
Model=HunyuanVideo, Pa...
2026.04
14,400
0.1
RoPE
Model=HunyuanVideo, Pa...
2026.04
14,410
-
RoME
Model=HunyuanVideo, Pa...
2026.04
40,100
0.1
RoPE
Model=HunyuanVideo, Pa...
2026.04
40,120
-
Feedback
Search any
task
Search any
task
