List your company

Audio-driven portrait video generation on PortraitOneMin (test)

42.3FPSOurs
-1.41129.936921.28532.6331Jun 1, 2026

Evaluation results

MethodLinks
OursM (number of reference images)=1, Resolution=512x512, Hardware=Single H100 GPU2026.0642.38.5376.6190.64891.964
OursM (number of reference images)=2, Resolution=512x512, Hardware=Single H100 GPU2026.0642.38.4386.6880.67781.517
OursM (number of reference images)=3, Resolution=512x512, Hardware=Single H100 GPU2026.0642.38.5466.6480.65973.693
EchoMIMIC-DistilledM (number of reference images)=1, Resolution=512x512, Hardware=Single H100 GPU2026.0613.35.5319.1870.201201.899
SonicM (number of reference images)=1, Resolution=512x512, Hardware=Single H100 GPU2026.061.78.1857.0310.59895.047
EchoMIMICM (number of reference images)=1, Resolution=512x512, Hardware=Single H100 GPU2026.061.44.8639.5940.208177.141
HalloM (number of reference images)=1, Resolution=512x512, Hardware=Single H100 GPU2026.061.26.7218.2750.21179.072
Hallo2M (number of reference images)=1, Resolution=512x512, Hardware=Single H100 GPU2026.061.26.8298.2440.196162.672
FantasyTalkingM (number of reference images)=1, Resolution=512x512, Hardware=Single H100 GPU2026.060.36————
Hallo3M (number of reference images)=1, Resolution=512x512, Hardware=Single H100 GPU2026.060.276.8368.7240.301175.34