Promote Sign in Sign up

Multimodal model

PersonaLive

PersonaLive is a real-time diffusion model for expressive portrait image animation in live streaming. It is built to turn a single portrait into continuous, streamable talking-head motion driven by input video, and is specifically designed for infinite-length generation rather than short fixed clips.

GVC Lab Multimodal Open weights apache-2.0
Visit model website ↗ Hugging Face
Type
Multimodal
Weights
Open
Likes
140
Pipeline
image to video
License
apache-2.0
Library
diffusers

Model hub

huaichang/PersonaLive

Repo
huaichang/PersonaLive
Access
Public
Technical tags and languages
diffusers onnx portrait-animation real-time diffusion image-to-video
Open on Hugging Face

Papers

1

About GVC Lab

1

GVC Lab (Generative & intelligent Visual Computing Lab) is an AI research laboratory at Great Bay University in Dongguan, China. Led by Prof. Xiaodong Cun, the lab focuses on animation, interactivity, intelligence, and visual representation — using generative AI to advance the movie and game industries. Research spans video generation, 3D Gaussian splatting, portrait animation, and video anomaly understanding.