Verified80% confidenceFactTime unknown
The Wan (万象) video generation model is based on the DiT (Diffusion Transformer) architecture.
6
Sources
80%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
ComfyUI-WanVideoWrapper：一文搞懂万象视频生成节点的安装与使用
githubkijai
Related Entities
Related Claims
Unverified文生视频模型通常基于扩散变换器（Diffusion Transformer）架构，将运动先验与外观风格解耦处理85% similarUnverifiedModern video diffusion models typically adopt U-Net or DiT (Diffusion Transformer) architectures to predict the noise added at each step.80% 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).79% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/29016API
curl https://kongchang.com/api/v1/knowledge/claims/29016MCP
get_claim(id=29016)