Unverified50% confidenceFactExact time
潜在扩散模型（LDM）是Stable Diffusion采用的架构，原始图像由VAE编码为约原始尺寸1/8大小的潜在向量
1
Sources
50%
Confidence
Long-term
Relevance
7/24/2026
First Seen
Sources
Related Claims
VerifiedStable Diffusion is built on the Latent Diffusion Model (LDM) architecture78% similarUnverifiedStable Diffusion 基于去噪扩散概率模型（DDPM）理论，将扩散过程从像素空间转移到低维潜在空间，由VAE负责编解码，CLIP模型将文本提示编码为语义向量76% similarVerifiedStable Diffusion基于潜在扩散模型（Latent Diffusion Model），通过在压缩的潜在空间中进行去噪过程来生成高质量图像69% similarUnverifiedRepaint集成了离线Stable Diffusion及其他神经网络能力；Stable Diffusion是由Stability AI于2022年发布的开源图像生成模型，采用潜在扩散模型（LDM）架构68% similarUnverifiedStable Diffusion Poxian Edition预装了SD基础模型和多种LoRA风格模型67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/605024API
curl https://kongchang.com/api/v1/knowledge/claims/605024MCP
get_claim(id=605024)