Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training

TL;DR

Muses introduces a novel, training-free approach for creating diverse, realistic fantasy 3D creatures by leveraging skeletal structures and a structured pipeline, outperforming prior methods in fidelity and coherence.

Contribution

This work presents the first training-free, skeleton-guided pipeline for 3D creature generation, enabling flexible, high-quality, and out-of-domain 3D asset creation without manual intervention.

Findings

Achieves state-of-the-art visual fidelity and textual alignment.

Enables flexible 3D object editing.

Outperforms existing methods in realism and coherence.

Abstract

We present Muses, the first training-free method for fantastic 3D creature generation in a feed-forward paradigm. Previous methods, which rely on part-aware optimization, manual assembly, or 2D image generation, often produce unrealistic or incoherent 3D assets due to the challenges of intricate part-level manipulation and limited out-of-domain generation. In contrast, Muses leverages the 3D skeleton, a fundamental representation of biological forms, to explicitly and rationally compose diverse elements. This skeletal foundation formalizes 3D content creation as a structure-aware pipeline of design, composition, and generation. Muses begins by constructing a creatively composed 3D skeleton with coherent layout and scale through graph-constrained reasoning. This skeleton then guides a voxel-based assembly process within a structured latent space, integrating regions from different objects. Finally, image-guided appearance modeling under skeletal conditions is applied to generate a style-consistent and harmonious texture for the assembled shape. Extensive experiments establish Muses' state-of-the-art performance in terms of visual fidelity and alignment with textual descriptions, and potential on flexible 3D object editing. Project page: https://luhexiao.github.io/Muses.github.io/.