Viggle AI: How to generate videos with controllable character movements

Author:neo yang Time:2024/05/13 Read: 8817

Video generation models such as Sora and Stable Video Dissfusion often face the problem of being unable to accurately control the output video, especially in terms of character movements. The controllable video model can accurately control the character movements in the video through prompt words. Viggle AI, as the first video-3D model with actual physical understanding capabilities, can freely control character movements and is embedded in the Discord platform. This controllable video technology will significantly reduce the cost of digital human products and enable diversified digital human video creation.

Overview

There is a problem with video generation models such as Sora and Stable Video Dissfusion, that is, the generated videos cannot be precisely controlled. This is especially obvious in terms of character movements.

What is a controllable video model?

A video generation model that accurately controls character movements and other behaviors through prompt words is a controllable video generation model.

What is Viggle AI?

Viggle AI claims to be the first video-based 3D model with actual physics understanding. It can control the movements of any character at will.

Viggle AI’s official website:https://www.viggle.ai/

How to use Viggle AI?

Viggle AI currently lives in discord.

You can join:https://discord.com/channels/1181076253172842537/@home

Example of a video generated by Viggle AI

Summarize

Controllable videos will bring about great changes to current digital human realization technology, greatly reducing the cost of a digital human product. It will also produce many digital human videos that were difficult to achieve before.

tags:AIGC