Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Talking-head synthesis on Conver-3D YouTube (test)
Loading...
2.76
FDD
ViBES
1.698
8.8665
16.035
23.2035
Dec 16, 2025
FDD
MOD
LVE
Updated 4d ago
Evaluation Results
Method
Method
Links
FDD
MOD
LVE
ViBES
Type=Multi Task, Train...
2025.12
2.76
8.27
12.88
FaceDiffuser
Type=Audio → Face, Tra...
2025.12
2.96
9.93
14.62
SelfTalk
Type=Audio → Face, Tra...
2025.12
11.56
25.45
23.44
ARTalk
Type=Audio → Face, Tra...
2025.12
11.6
9.04
14.42
CodeTalker
Type=Audio → Face, Tra...
2025.12
17.72
10.9
16.19
ScanTalk
Type=Audio → Face, Tra...
2025.12
21.02
15.81
35.08
MultiTalk
Type=Audio → Face, Tra...
2025.12
24.42
2.48
16.2
DiffPoseTalk
Type=Audio → Face, Tra...
2025.12
28.4
8.41
12.34
UniTalker
Type=Audio → Face, Tra...
2025.12
29.31
2.07
15.3
Feedback
Search any
task
Search any
task