Unverified80% confidenceFactExact time
OpenAI Sora基于Diffusion Transformer架构，在视觉质量上取得突破但仍频繁出现液体无故消失、刚体穿透等物理幻觉
1
Sources
80%
Confidence
Long-term
Relevance
5/29/2026
First Seen
Sources
Gemini Omni: How Powerful Is AI Video Generation That Understands Physics?
twitterGeminiApp5/29/2026
Related Entities
Related Claims
VerifiedOpenAI's Sora uses a diffusion Transformer architecture and is known for high-quality text-to-video generation.67% similarUnverifiedSora adopts the Diffusion Transformer (DiT) architecture, introducing the Transformer's global attention mechanism into the diffusion framework.65% similarUnverifiedVideo generation models such as OpenAI's Sora and Kuaishou's Kling also adopt a technical approach similar to DiT.64% similarPartially VerifiedSora adopts the DiT (Diffusion Transformer) architecture, compressing video into spatiotemporal patch sequences before feeding them into a Transformer, replacing the traditional U-Net with a Transformer as the denoising backbone network.62% similarVerifiedOpenAI's Sora and Stability AI's Stable Video Diffusion are both influenced by the DiT architecture.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/183API
curl https://kongchang.com/api/v1/knowledge/claims/183MCP
get_claim(id=183)