디퓨전
![[논문리뷰] High-Resolution Image Synthesis with Latent Diffusion Models (LDM, Latent Diffusion)](https://img1.daumcdn.net/thumb/R750x0/?scode=mtistory2&fname=https%3A%2F%2Fblog.kakaocdn.net%2Fdn%2FnSRa5%2FbtsMtswxVpS%2FxTyXjQoDJR5CzJdspXlNrk%2Fimg.png)
[논문리뷰] High-Resolution Image Synthesis with Latent Diffusion Models (LDM, Latent Diffusion)
High-Resolution Image Synthesis with Latent Diffusion ModelsBy decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism tarxiv.org내용은 별거 없다. input image의 전체 domain에서 수행하던 diffusion 연산을 latent space에서 한다...