The accelerated inverse design of complex material properties—such as identifying a material with a given stress–strain response over a nonlinear deformation path—holds great potential for addressing challenges from soft robotics to biomedical implants and impact mitigation. Although machine learning models have provided such inverse mappings, they are typically restricted to linear target properties such as stiffness. Here, to tailor the nonlinear response, we show that video diffusion generative models trained on full-field data of periodic stochastic cellular structures can successfully predict and tune their nonlinear deformation and stress response under compression in the large-strain regime, including buckling and contact. Key to success is to break from the common strategy of directly learning a map from property to design and to extend the framework to intrinsically estimate the expected deformation path and the full-field internal stress distribution, which closely agree with finite element simulations. This work thus has the potential to simplify and accelerate the identification of materials with complex target performance.

复杂材料特性的加速逆向设计（例如识别在非线性变形路径上具有给定应力应变响应的材料）在解决从软机器人到生物医学植入物和冲击缓解的挑战方面具有巨大潜力。尽管机器学习模型提供了此类逆映射，但它们通常仅限于线性目标属性，例如刚度。在这里，为了定制非线性响应，我们表明，在周期性随机细胞结构的全场数据上训练的视频扩散生成模型可以成功预测和调整大应变状态下压缩下的非线性变形和应力响应，包括屈曲和接触。成功的关键是打破直接学习从属性到设计的映射的常见策略，并将框架扩展为内在估计预期变形路径和全场内应力分布，这与有限元模拟非常一致。因此，这项工作有可能简化和加速具有复杂目标性能的材料的识别。