List your company

Audio-to-Video on VGGSound (test)

150.26gFVDAVTok-A2V
124.806296.6205468.435640.2495Jun 29, 2026

Evaluation results

MethodLinks
AVTok-A2VGen Type=AR, #Param Tokenizer=208.4M, #Param Generator=632.0M2026.06150.26—1.3170.143
TempoTokensGen Type=Diff, #Param Tokenizer=83.7M, #Param Generator=1.9B2026.06786.61—1.3590.132