Skip to content

EchoMimicV2

Generate half-body animation from audio and poses

Visit official site

What EchoMimicV2 is

The technique is described as a half-body human animation method that turns a reference image, audio clip and gestures into a coherent animation video.

What you can do with it

  • Generate animation from a reference image and audio
  • Enhance facial and hand expressiveness
  • Simplify earlier complex animation workflows

Pros & cons

✓ What we like

  • Conditional redundancy is reduced in the workflow
  • A new benchmark for half-body animation is provided

! What to watch out for

  • Input needs an image, audio and gesture sequence
  • The head attention module can be omitted at inference

FAQ

What inputs are needed?

A reference image, an audio clip and a sequence of hand gestures are named.

Who developed it?

The material names the terminal technology department of Ant Group.

Last reviewed: 2026-11-15

More AI video generation tools

View all →

How we review