MultiAnimate: Pose-Guided Image Animation Made Extensible

TL;DR

MultiAnimate introduces a diffusion transformer-based framework with novel components for scalable, multi-character pose-guided image animation, achieving state-of-the-art results and generalizing beyond training scenarios.

Contribution

It presents a new extensible multi-character animation framework with Identifier Assigner and Identifier Adapter, enabling generalization and improved performance.

Findings

Achieves state-of-the-art multi-character animation results.

Generalizes from two-character training to multi-character scenarios.

Outperforms existing diffusion-based baselines.

Abstract

Pose-guided human image animation aims to synthesize realistic videos of a reference character driven by a sequence of poses. While diffusion-based methods have achieved remarkable success, most existing approaches are limited to single-character animation. We observe that naively extending these methods to multi-character scenarios often leads to identity confusion and implausible occlusions between characters. To address these challenges, in this paper, we propose an extensible multi-character image animation framework built upon modern Diffusion Transformers (DiTs) for video generation. At its core, our framework introduces two novel components-Identifier Assigner and Identifier Adapter - which collaboratively capture per-person positional cues and inter-person spatial relationships. This mask-driven scheme, along with a scalable training strategy, not only enhances flexibility but also enables generalization to scenarios with more characters than those seen during training. Remarkably, trained on only a two-character dataset, our model generalizes to multi-character animation while maintaining compatibility with single-character cases. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in multi-character image animation, surpassing existing diffusion-based baselines.