Wukong's 72 Transformations: High-fidelity Textured 3DMorphing via Flow Models

We present WUKONG, a novel training-free framework for high-fidelity textured 3D morphing that takes a pair of source and target prompts (image or text) as input. Unlike conventional methods--which rely on manual correspondence matching and deformation trajectory estimation (limiting generalization and requiring costly preprocessing)--WUKONG leverages the generative prior of flow-based transformers to produce high-fidelity 3D transitions with rich texture details. To ensure smooth shape transitions, we exploit the inherent continuity of flow-based generative processes and formulate morphing as an optimal transport barycenter problem. We further introduce a sequential initialization strategy to prevent abrupt geometric distortions and preserve identity coherence. For faithful texture preservation, we propose a similarity-guided semantic consistency mechanism that selectively retains high-frequency details and enables precise control over blending dynamics. This empowers WUKONG to support both global texture transitions and identitypreserving texture morphing, catering to diverse generation needs. Extensive quantitative and qualitative evaluations demonstrate that WUKONG significantly outper-Corresponding author.