List your company

Text-to-Sounding-Video Generation on AVSync15

765.74FVDBridgeDiT
717.36081,043.92041,370.481,697.0396Oct 3, 2025

Evaluation results

MethodLinks
BridgeDiTProcess=T → VA2025.10765.7421.335.341.328.5235.9534.5927.5
Wan + SDAProcess=T → V ∥ T → A2025.10828.3322.5611.93.1728.1230.7826.2220.5
Wan + MMAudioProcess=T → V + V → A2025.10828.3322.567.981.428.1234.6433.524.3
Wan + SeeingHearingProcess=T → V + V → A2025.10828.3322.5614.212.8928.1225.5235.8720.8
Wan + ThinkSoundProcess=T → V + V → A2025.10828.3322.5617.315.5828.1230.9220.716.9
Wan + PrismAudioProcess=T → V + V → A2025.10828.3322.569.792.3428.1233.5325.2523.3
JavisDiTProcess=T → VA2025.10878.723.2313.483.528.0522.9920.7515.8
MTVProcess=T → VA2025.10982.0924.616.463.5327.6621.2215.8414.9
JointDiTProcess=T → I + I → VA2025.10992.7125.26.511.7729.9430.3434.1715.6
SSVGProcess=T → VA2025.101,028.7831.4414.354.3525.7823.6722.4512.6
CoDiProcess=T → VA2025.101,387.1439.2416.565.2424.9617.9410.798.1
SDA + TempoTokenProcess=T → A + A → V2025.101,516.5342.311.93.1720.5630.7817.6321.5
SDA + TPosProcess=T → A + A → V2025.101,975.2292.9511.93.1718.6430.7825.4517.6