🔊 Text-Prompted Generative Audio Model

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

The official code of paper "LVCD: Reference-based Lineart Video Colorization with Diffusion Models"

[ICCV, 2023] Multiple humans in 3D captured by dynamic and static cameras in 4K.

Official repo of "Time Reversal Fusion" (ECCV2024)