Paper : https://arxiv.org/pdf/2303.10137AuthorsSea AI Lab +Tsinghua Univ, ICLR’24Main IdeaDiffusion Model을 위한 watermarking 방법을 정리하고, 분석한 논문입니다.Tasks : Unconditional Generation, T2I GenerationResults : FFHQ, AFHQv2, ImageNet-1K(64x64), CIFAR-10(32x32)0. Before Start...   a. Defense Model    b. Threat Model1. Problem2. Approach    a. Unconditional & Class-conditional Generation   b. Text-To-Image ..

Paper : https://openaccess.thecvf.com/content/CVPR2023/html/Blattmann_Align_Your_Latents_High-Resolution_Video_Synthesis_With_Latent_Diffusion_Models_CVPR_2023_paper.htmlAuthorsNvidia + Andreas Blattmann et al, Toronto Univ., CVPR’23 DecMain IdeaLDM을 기반으로 computation & memory 측면에서 효율적인 접근으로 Vido Generation을 했습니다.기존 pre-trained된 image LDM을 활용temporal layer를 image에 align함으로써High Resolution & Long-..