Unverified60% confidenceFactExact time
In text-to-video model architectures, early models mostly adopted U-Net structures (such as Stable Video Diffusion), while new-generation models tend to use Transformer architectures (such as DiT).
2
Sources
60%
Confidence
Long-term
Relevance
8/8/2026
First Seen
Sources
Related Claims
Unverified早期视频生成模型基于U-Net架构，而扩散变换器将Transformer的注意力机制引入扩散过程79% similarUnverifiedModern video diffusion models typically adopt U-Net or DiT (Diffusion Transformer) architectures to predict the noise added at each step.79% similarVerifiedThe Wan (万象) video generation model is based on the DiT (Diffusion Transformer) architecture.79% similarVerifiedCompared to earlier U-Net-based diffusion models, the DiT architecture has stronger temporal consistency when processing long-sequence video frames.79% similarUnverifiedState-of-the-art video generation models such as Sora and Stable Video Diffusion both adopt DiT or its variants75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/707178API
curl https://kongchang.com/api/v1/knowledge/claims/707178MCP
get_claim(id=707178)