Unverified60% confidenceFactExact time
Sora adopts a Video Diffusion Transformer (DiT), compressing video into spatiotemporal patches before modeling the diffusion process.
2
Sources
60%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
UnverifiedState-of-the-art video generation models such as Sora and Stable Video Diffusion both adopt DiT or its variants84% similarUnverifiedSora introduces a video compression network that compresses video into low-dimensional spatiotemporal patches, then performs diffusion generation in that space.81% similarUnverifiedOpenAI Sora 引入了视频压缩网络与 Transformer 结合的时空补丁机制，将视频拆解为跨越空间与时间的三维补丁78% similarUnverifiedSora's core breakthrough lies in understanding video as a sequence of spacetime patches, unifying the handling of different resolutions and durations.78% similarUnverified2023年后，以Stable Video Diffusion、Sora为代表的时序扩散模型开始将视频理解为时空连续体，能够在潜空间中同时建模多帧之间的运动关系77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/515693API
curl https://kongchang.com/api/v1/knowledge/claims/515693MCP
get_claim(id=515693)