# MagicAvatar

**Multimodal Avatar Generation and Animation**

Introducing MagicAvatar, a multi-modal framework capable of converting various input modalities — text, video, and audio — into motion signals that subsequently generate/ animate an avatar. 

{% embed url="<https://magic-avatar.github.io/>" %}
<https://magic-avatar.github.io/>
{% endembed %}

**Introduction Video:**

{% embed url="<https://www.youtube.com/watch?v=UN7W5oKmWNA&t=>" %}

**Text-guided Avatar Generation.**

Create avatar(s) with simple text prompts. Text prompt, Generated motion, Generated video

**Video-guided Avatar Generation**&#x20;

Given a source video, create avatar(s) that follows the given motion.

**Multimodal Avatar Animation**

Animate an avatar of a specific subject. Identity, Driving signal, Motion Generated video,&#x20;

**Audio-guided Avatar Generation (coming soon)**&#x20;

Create an avatar based on audio input.