Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Diffusion Transformer Networks
Authors:
Preprint
Abstract
Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait, and generating immersive, realistic backgrounds. In this paper, we introduce the first application of a pretrained transformer-based video generative model that demonstrates strong generalization capabilities and generates highly dynamic, realistic videos for portrait animation, effectively addressing these challenges. The adoption of a new video backbone model makes previous U-Net-based methods for identity maintenance, audio conditioning, and video extrapolation inapplicable. To address this limitation, we design an identity reference network consisting of a causal 3D VAE combined with a stacked series of transformer layers, ensuring consistent facial identity across video sequences. Additionally, we investigate various speech audio conditioning and motion frame mechanisms to enable the generation of continuous video driven by speech audio. Our method is validated through experiments on benchmark and newly proposed wild datasets, demonstrating substantial improvements over prior methods in generating realistic portraits characterized by diverse orientations within dynamic and immersive scenes. Further visualizations and the source code are available at: https://fudan-generative-vision.github.io/hallo3/.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Tora: Trajectory-oriented Diffusion Transformer for Video Generation2025
- VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis2025
- VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior2025
- Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance2024
- EMO: Emote Portrait Alive Generating Expressive Portrait Videos with Audio2Video Diffusion Model Under Weak Conditions2024
- AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding2024
- VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time2024
- wav2vec: Unsupervised Pre-Training for Speech Recognition2019
- Face recognition based on fitting a 3D morphable modelIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003