Stablediffusion SD AnimateDiff One-Click Video Generation: A Super Simple Tutorial

Installation process

Latest version:Stable-diffusion
Dependencies:Python 3.10.6, Git
Chinese version:Chinese plugin
Main plugins:SD AnimateDiff, adetailer
Small model:mm_sd_v15_v2
After downloading, place the model file in the stable-diffusion-webui/extensions/sd-webui-animatediff/model/ folder
Large model:majicmixRealistic_v6
After downloading, place the large model file in the stable-diffusion-webui-1.7.0\models\Stable-diffusion folder

Finally, after the installation is complete, restart the Stable-diffusion UI and select the model majicmixRealistic_v6


Condensed illustrated tutorial

Image-to-video uses the open-source, free GitHub plugin Enable animatediff. You need to configure your network properly before downloading.

Let's first look at the effect image of one frame



The method is the same as the previous text-to-image generation, using prompts to generate. You can refer to the following format



Positive prompt

1. ((pure white background )),Best quality,masterpiece,ultra high res,raw photo,beautiful and aesthetic,(photorealistic:1.4),1girl,full-body composition,striking perspective,Danceing,high-waisted shorts,ruffled blouse

复制代码

Negative prompt

1. FastNegativeV2 EasyNegative

复制代码

Generation process and display; if you need higher definition, you can enable high-definition resolution




You can change to your own model; there is no need to download a model separately