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 identity-preserving texture morphing, catering to diverse generation needs. Extensive quantitative and qualitative evaluations demonstrate that WUKONG significantly outperforms state-of-the-art methods, achieving superior results across diverse geometry and texture variations.

翻译：本文提出WUKONG，一种新颖的无训练高保真纹理三维变形框架，以源提示与目标提示（图像或文本）对作为输入。与传统方法——依赖人工对应匹配与变形轨迹估计（泛化能力受限且需昂贵预处理）——不同，WUKONG利用基于流的Transformer的生成先验，生成具有丰富纹理细节的高保真三维过渡。为确保平滑的形状过渡，我们利用基于流的生成过程固有的连续性，并将变形建模为最优传输重心问题。我们进一步引入序列初始化策略以防止突发的几何畸变并保持身份一致性。为实现忠实的纹理保持，我们提出相似性引导的语义一致性机制，该机制选择性地保留高频细节并实现对混合动态的精确控制。这使得WUKONG能够同时支持全局纹理过渡与身份保持的纹理变形，满足多样化的生成需求。大量的定量与定性评估表明，WUKONG显著优于现有最先进方法，在多样化的几何与纹理变化上均取得了更优的结果。