New AI model generates 45-minute lip-synced video from one photo and runs in real time

THE DECODER / 4/14/2026

📰 NewsSignals & Early TrendsModels & Research

共有:

Key Points

The research project LPM 1.0 can generate a 45-minute, lip-synced talking-video sequence from a single input photo while producing facial expressions and emotional reactions.
The model is described as running in real time, enabling interactive generation rather than only offline rendering.
The output includes synchronized mouth movement aligned to speech content, focusing on avatar-style character animation driven by static imagery.
Despite the strong capabilities, the work is still positioned as a research prototype rather than a publicly available product.

A single image becomes a talking character: LPM 1.0 generates real-time video with lip sync, facial expressions, and emotional reactions. For now, it remains a research project.

The article New AI model generates 45-minute lip-synced video from one photo and runs in real time appeared first on The Decoder.