CIntellifusion/MultiWorld
Generates consistent multi-agent videos from multiple viewpoints
View on index · View in 3D Map
Related repos
- Generate video and 3D scenes via unified world modeling
- Reconstructs 3D worlds from video diffusion models
- Compose video via autonomous agents
- HTML-based video rendering for AI agents
- Interactive world model from large-scale human videos
- Framework for multimodal conversational agents
- Ensemble of AI agents for automated video editing
- Curates research on video generation for world modeling
- Video world model with 4D geometric control over camera and motion
- Video generation from text and depth
