Unifying Human, World, and Interaction with Generative AI
-
FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction
Paper • 2509.21657 • Published • 4 -
FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
Paper • 2504.04842 • Published • 35 -
FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework
Paper • 2509.01232 • Published -
FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation
Paper • 2508.11255 • Published • 11
