Deforum AI Full Tutorial: Text To Video Animation
Create massively trending animations using Deforum AI with stable diffusion!
This tutorial will fully cover the Stable Diffusion local install as well as utilizing the Deforum extension to create AI Text to Video masterpieces!
Deforum allows users to input a starter image and build upon that image using text prompts.
Deforum takes the "init" or initial still photograph and allows the user to select a number of frames for their new text to video animation.
Then, Deforum prompts the user to add frame based prompts.
Ex:
Frame "0" = init
Frame "30" = "anamorphic lion man pointing finger"
Frame "60" = "Fiery hero transition"
etc etc
Deforum is a wonderful free ai text to video tool you can install and use locally with no subscription or API key.
Link 1:
python.org
Link 2:
https://github.com/EmpireMediaScience/A1111-Web-UI-Installer/releases
Link 3:
https://civitai.com/models/4331/protogen-nova-experimental-model-official-release
Parameters:
Translation X
0:(0.65), 25:(0.55)
Translation Z
0:(0.2), 60:(10), 300:(15)
Rotation 3D X
0:(0), 60:(0), 90:(0.5), 180:(0.5), 300:(0.5)
Rotation 3D Y
0:(0), 30:(-3.5), 90:(-2.5), 180:(-2.8), 300:(-2), 420:(0)
Rotation 3D Z
0:(0), 60:(0.2), 90:(0), 180:(-0.5), 300:(0), 420:(0.5), 500:(0.8)
Noise Schedule
0:(-0.06*(cos(3.141*t/15)**100)+0.06)