Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Text-to-Video Generation on Unspecified Text-to-Video Dataset (test)
Loading...
0.732
Clip-score
Text2Video-zero
0.69872
0.70736
0.716
0.72464
Dec 15, 2023
Clip-score
GFLOPs/image
Latency (s/image) (Unet)
Latency (s/image) (SD)
Updated 3d ago
Evaluation Results
Method
Method
Links
Clip-score
GFLOPs/image
Latency (s/image) (Unet)
Latency (s/image) (SD)
Text2Video-zero
T (Sampling Steps)=50
2023.12
0.732
39,670
-
-
Text2Video-zero + Faster Diffusion
T (Sampling Steps)=50
2023.12
0.731
30,690
-
-
VideoFusion
T (Sampling Steps)=50
2023.12
0.7
224,700
-
-
VideoFusion + Faster Diffusion
T (Sampling Steps)=50
2023.12
0.7
148,680
-
-
Feedback
Search any
task
Search any
task