Verified90% confidenceFactExact time
OpenAI's Sora uses a diffusion Transformer architecture and is known for high-quality text-to-video generation.
7
Sources
90%
Confidence
Long-term
Relevance
5/28/2026
First Seen
Sources
Gemini Omni Video Editing Arrives in India: An Upload-and-Edit AI Experience
twitterGeminiApp5/28/2026
Related Entities
Related Claims
UnverifiedOpenAI 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82% similarVerifiedThe Wan (万象) video generation model is based on the DiT (Diffusion Transformer) architecture.76% similarUnverifiedMainstream video generation models such as Sora and CogVideoX widely adopt the DiT or its variant architectures, marking the transition of video generation technology from the UNet era to the Transformer era.76% similarUnverifiedDiffusion models excel in image quality and controllability, while Transformer architectures have greater potential for long-video coherence and understanding of the physical world.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1796API
curl https://kongchang.com/api/v1/knowledge/claims/1796MCP
get_claim(id=1796)