Unverified50% confidenceFactExact time
DiT架构由Peebles和Xie在2023年提出，用纯Transformer替换U-Net，将图像或视频切分为patch token统一处理
1
Sources
50%
Confidence
Long-term
Relevance
8/27/2026
First Seen
Sources
Related Entities
Related Claims
Partially 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.72% similarVerifiedFLUX adopts a DiT (Diffusion Transformer) architecture, replacing the traditional U-Net structure with a pure Transformer.72% similarUnverifiedThe DiT architecture replaces the traditional U-Net with a Transformer as the diffusion model backbone, enabling the capture of long-range cross-frame dependencies at the patch level.70% similarUnverifiedBitNet是微软研究院于2023年提出的架构级创新，核心思想是在Transformer架构中将线性层权重替换为1-bit表示69% similarVerifiedLTX 2.3 adopts a Transformer-based diffusion architecture (DiT, Diffusion Transformer), which has stronger temporal consistency modeling capabilities compared to the traditional U-Net architecture.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/810068API
curl https://kongchang.com/api/v1/knowledge/claims/810068MCP
get_claim(id=810068)