Apps & Tools
JVT
Simple pixel-space video diffusion with a transformer architecture.
Is this your creation?
PlayableOpen source
Description
JVT (Just Video Transformer) generates videos directly in pixel space using a simple DiT-style transformer architecture. It includes training and inference code for unconditional, class-conditioned, and camera-controlled generation across datasets like UCF-101 and RealEstate10K.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.