PERSE: Personalized 3D Generative Avatars from A Single Portrait Paper β’ 2412.21206 β’ Published 2 days ago β’ 8
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization Paper β’ 2412.21037 β’ Published 2 days ago β’ 19
Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis Paper β’ 2412.15322 β’ Published 13 days ago β’ 16