Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency

TL;DR

Loopy is an end-to-end audio-only conditioned video diffusion model that captures long-term motion dependencies to generate natural and high-quality portrait videos without manual motion templates.

Contribution

The paper introduces Loopy, a novel diffusion model with temporal modules that leverage long-term motion data, eliminating the need for manual spatial motion constraints.

Findings

Outperforms recent audio-driven portrait diffusion models

Produces more lifelike and high-quality portrait videos

Effectively captures long-term motion dependencies

Abstract

With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both the naturalness of motion and the synthesis of portrait details. Due to the limited control of audio signals in driving human motion, existing methods often add auxiliary spatial signals to stabilize movements, which may compromise the naturalness and freedom of motion. In this paper, we propose an end-to-end audio-only conditioned video diffusion model named Loopy. Specifically, we designed an inter- and intra-clip temporal module and an audio-to-latents module, enabling the model to leverage long-term motion information from the data to learn natural motion patterns and improving audio-portrait movement correlation. This method removes the need for manually specified spatial motion templates used in existing methods to constrain motion during inference. Extensive experiments show that Loopy outperforms recent audio-driven portrait diffusion models, delivering more lifelike and high-quality results across various scenarios.