{"width":"100%","version":"1.0","blog_title":"\u30aa\u30e0\u30e9\u30a4\u30b9\u306e\u5099\u5fd8\u9332","categories":[],"image_url":"https://docs.google.com/drawings/d/e/2PACX-1vSaeH7mpNOOLvoHYOZ6WfFbMTA1UhZk5U2heXDwCOVWXcMINpdK0Ab4SARXgfDbau3DJ4XiGjIUGS8C/pub?w=765&h=560","published":"2025-05-19 10:48:24","provider_name":"Hatena Blog","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fyhayato1320.hatenablog.com%2Fentry%2F2025%2F05%2F19%2F104824\" title=\"\u3010\u6df1\u5c64\u5b66\u7fd2\u3011IV-VAE - \u30aa\u30e0\u30e9\u30a4\u30b9\u306e\u5099\u5fd8\u9332\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","url":"https://yhayato1320.hatenablog.com/entry/2025/05/19/104824","title":"\u3010\u6df1\u5c64\u5b66\u7fd2\u3011IV-VAE","provider_url":"https://hatena.blog","author_name":"yhayato1320","type":"rich","author_url":"https://blog.hatena.ne.jp/yhayato1320/","blog_url":"https://yhayato1320.hatenablog.com/","description":"Index Index IV-VAE Latent Video Diffusion Model / LVDM \u6539\u5584\u70b9 Keyframe-based Temporal Compression / KTC) Group Causal Convolution / GCConv \u53c2\u8003 IV-VAE Video Generation Model\u3001\u7279\u306b Latent Video Diffusion Model / LVDM \u306e\u6539\u826f. \u65e2\u5b58\u306e Video Variational Autoencoder (Video VAE) \u304c\u62b1\u3048\u308b\u3001\u4e8b\u524d\u306b\u8a13\u7df4\u3055\u308c\u305f\u753b\u50cfVAE\u304b\u3089\u306e\u521d\u671f\u5316\u306b\u3088\u308b\u6642\u9593\u5727\u7e2e\u80fd\u529b\u306e\u6291\u5236\u3084\u3001\u56e0\u679c\u69cb\u2026","height":"190"}