Promote Sign in Sign up

Multimodal model

AVTR 1

AVTR-1 is Avaturn Live’s avatar video model for real-time lip-synced speech and active-listening animation from a portrait image plus audio streams.

GOODSIZE Multimodal Closed other Gated
Visit model website ↗ Hugging Face
Type
Multimodal
Weights
Closed
Downloads
728
Likes
50
Pipeline
image to video
License
other

Model hub

avaturn-live/avtr-1

Repo
avaturn-live/avtr-1
Library
tensorrt
Access
Gated
Technical tags and languages
tensorrt onnx talking-head lip-sync avatar real-time audio-driven image-to-video
Open on Hugging Face

More from GOODSIZE

2

About GOODSIZE

1

Create realistic 3D avatar with a selfie, customize, export as 3D model. Developer? Integrate our avatar SDK into your app or metaverse.