Mechanical metamaterials, known for their periodic building blocks, are architected materials with exceptional properties and functions determined by their microstructures and constituent materials. Tailoring their microstructural heterogeneity unlocks the potential to achieve unprecedented bulk properties and functions. However, current mechanical metamaterial design considerably relies on experienced designers' inspiration through trial and error, while investigating their mechanical properties and responses entails time‐consuming mechanical testing or computationally expensive simulations. Recent advances have led to the development of generative artificial intelligence (AI) for the design of metamaterial microstructures. Here, we proposed generative AI models based on image generation algorithms, such as generative adversarial networks and diffusion models, to generate mechanical metamaterials with various controllable mechanical properties. Furthermore, by combining image generation algorithms with large language models, we demonstrated the capability to generate metamaterials from text prompts. We demonstrated how state-of-the-art AI can be harnessed to accelerate and even revolutionize material design and discovery, aiming to inspire researchers across multiple disciplines, such as materials science, mechanical engineering, and chemistry.
Zheng et al. (Wed,) studied this question.