EchoMimicV2
Ant Group's half-body animated digital humans from one image + audio
From Ant Group: generate half-body animated digital-human videos from one image plus audio.
AI video generation, digital humans, and video restoration.
Key features
- Audio-driven semi-body human animation (portrait and half-body)
- Simplified landmark conditioning; accelerated 9x inference on A100
- Gradio UI and ComfyUI integration
- Reference image and pose alignment demo
- EMTD dataset list and processing scripts released
Good for
- Animating portraits or half-body figures from speech audio
- Creating virtual presenters or characters
Stack & tags
PythonGradiohuman-animationaudio-driventalking-headopen-weightscomfyuigradiohalf-body
Similar open-source projects
Hyperframes
★ 55,468Write HTML. Render video. Built for agents — HeyGen's open-source video framework
Hypit
★ 18,649Clone any viral video with AI agents — swap the face, the words, the B-roll, ship 100 variants