Animate Any Character in Any World

TL;DR

AniX enables realistic, controllable character animation in any environment by combining static world generation with user-directed, open-ended actions, producing high-quality, coherent videos.

Contribution

The paper introduces AniX, a novel framework that supports user-specified characters performing diverse actions in static scenes, extending controllable-entity models with open-ended behavior capabilities.

Findings

High visual fidelity in generated videos

Effective control of character actions via natural language

Strong generalization across different characters and actions

Abstract

Recent advances in world models have greatly enhanced interactive environment simulation. Existing methods mainly fall into two categories: (1) static world generation models, which construct 3D environments without active agents, and (2) controllable-entity models, which allow a single entity to perform limited actions in an otherwise uncontrollable environment. In this work, we introduce AniX, leveraging the realism and structural grounding of static world generation while extending controllable-entity models to support user-specified characters capable of performing open-ended actions. Users can provide a 3DGS scene and a character, then direct the character through natural language to perform diverse behaviors from basic locomotion to object-centric interactions while freely exploring the environment. AniX synthesizes temporally coherent video clips that preserve visual fidelity with the provided scene and character, formulated as a conditional autoregressive video generation problem. Built upon a pre-trained video generator, our training strategy significantly enhances motion dynamics while maintaining generalization across actions and characters. Our evaluation covers a broad range of aspects, including visual quality, character consistency, action controllability, and long-horizon coherence.