Expired60% confidenceFactExact time
The DiT architecture has become the common technical choice for mainstream video generation models such as Sora, Kling, and Wan.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/15/2026
First Seen
Valid until: 10/13/2026(expired)
Sources
Related Claims
UnverifiedVideo generation models such as OpenAI's Sora and Kuaishou's Kling also adopt a technical approach similar to DiT.78% 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% similarUnverifiedMainstream video generation models including Sora (OpenAI), Wan2.1 (Alibaba), and CogVideoX (Zhipu) have all adopted the DiT or its variant architecture.76% similarVerifiedThe Wan (万象) video generation model is based on the DiT (Diffusion Transformer) architecture.74% similarUnverifiedIn 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).72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/523819API
curl https://kongchang.com/api/v1/knowledge/claims/523819MCP
get_claim(id=523819)