X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio

TL;DR

X-Actor is a novel framework that generates emotionally expressive, long-form talking head videos from a single image and audio, capturing nuanced emotions with high fidelity and coherence over extended durations.

Contribution

It introduces a two-stage diffusion-based pipeline that models long-range facial motion from audio, enabling actor-quality, emotionally rich portrait animations from a single reference image.

Findings

Achieves state-of-the-art results in long-range, audio-driven portrait acting.

Produces cinematic-style performances with nuanced emotional expression.

Operates effectively without error accumulation over extended sequences.

Abstract

We present X-Actor, a novel audio-driven portrait animation framework that generates lifelike, emotionally expressive talking head videos from a single reference image and an input audio clip. Unlike prior methods that emphasize lip synchronization and short-range visual fidelity in constrained speaking scenarios, X-Actor enables actor-quality, long-form portrait performance capturing nuanced, dynamically evolving emotions that flow coherently with the rhythm and content of speech. Central to our approach is a two-stage decoupled generation pipeline: an audio-conditioned autoregressive diffusion model that predicts expressive yet identity-agnostic facial motion latent tokens within a long temporal context window, followed by a diffusion-based video synthesis module that translates these motions into high-fidelity video animations. By operating in a compact facial motion latent space decoupled from visual and identity cues, our autoregressive diffusion model effectively captures long-range correlations between audio and facial dynamics through a diffusion-forcing training paradigm, enabling infinite-length emotionally-rich motion prediction without error accumulation. Extensive experiments demonstrate that X-Actor produces compelling, cinematic-style performances that go beyond standard talking head animations and achieves state-of-the-art results in long-range, audio-driven emotional portrait acting.