Unverified50% confidenceFactExact time
文本扩散采用掩码扩散（Masked Diffusion）方案，用[MASK]token替代真实token模拟损坏状态，再训练模型恢复原始文本，以块为单位并行输出
1
Sources
50%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
VerifiedStable Diffusion's text guidance converts prompts into vectors through the CLIP text encoder.70% similarUnverified掩码扩散框架将加噪重新定义为token掩码替换，使扩散过程在离散文本域得以自洽68% similarUnverified研究者提出了掩码扩散（Masked Diffusion）、吸收态扩散（Absorbing Diffusion）等变体以解决文本离散空间的扩散挑战66% similarUnverifiedThe underlying architecture of mainstream text-to-image models such as Stable Diffusion, Midjourney, and DALL-E typically combines a diffusion model with a CLIP text encoder.64% similarUnverifiedPure text models are based on the Transformer architecture and only process tokenized text sequences, lacking the encoding pathway to convert pixel information into semantic representations.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/565264API
curl https://kongchang.com/api/v1/knowledge/claims/565264MCP
get_claim(id=565264)