OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

TL;DR

OmniHuman-1.5 introduces a novel framework that generates semantically coherent and expressive avatar animations by integrating multimodal large language models and a specialized multimodal fusion architecture.

Contribution

The paper presents a new approach combining multimodal large language models with a Pseudo Last Frame design for improved semantic understanding in avatar motion generation.

Findings

Achieves state-of-the-art lip-sync accuracy and motion naturalness.

Demonstrates strong semantic consistency with textual prompts.

Extends effectively to multi-person and non-human scenarios.

Abstract

Existing video avatar models can produce fluid human animations, yet they struggle to move beyond mere physical likeness to capture a character's authentic essence. Their motions typically synchronize with low-level cues like audio rhythm, lacking a deeper semantic understanding of emotion, intent, or context. To bridge this gap, \textbf{we propose a framework designed to generate character animations that are not only physically plausible but also semantically coherent and expressive.} Our model, \textbf{OmniHuman-1.5}, is built upon two key technical contributions. First, we leverage Multimodal Large Language Models to synthesize a structured textual representation of conditions that provides high-level semantic guidance. This guidance steers our motion generator beyond simplistic rhythmic synchronization, enabling the production of actions that are contextually and emotionally resonant. Second, to ensure the effective fusion of these multimodal inputs and mitigate inter-modality conflicts, we introduce a specialized Multimodal DiT architecture with a novel Pseudo Last Frame design. The synergy of these components allows our model to accurately interpret the joint semantics of audio, images, and text, thereby generating motions that are deeply coherent with the character, scene, and linguistic content. Extensive experiments demonstrate that our model achieves leading performance across a comprehensive set of metrics, including lip-sync accuracy, video quality, motion naturalness and semantic consistency with textual prompts. Furthermore, our approach shows remarkable extensibility to complex scenarios, such as those involving multi-person and non-human subjects. Homepage: \href{https://omnihuman-lab.github.io/v1_5/}