MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model with @Gradio demo local demo: https://t.co/ScsEU6oG64 This paper studies the human image animation task, which aims to generate a video of a certain reference identity following a particular motion… pic.twitter.com/JCOr0yCRZs — AK (@_akhaliq) December 4, 2023 モデル準備リリース時点では READMEにあるStableDiffusion V1.5とMSE-finetuned VA
![MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Modelを触る|ねご(Nego)](https://cdn-ak-scissors.b.st-hatena.com/image/square/1c46734594efe921ccb6f85a3b9de1c20620eb48/height=288;version=1;width=512/https%3A%2F%2Fd2l930y2yx77uc.cloudfront.net%2Fproduction%2Fsocial_images%2Fdbaff0b946972c6fa3dc1aa64535a9511b0542a9.png)