Recent advances in deep learning generative models (GMs) have created high capabilities in accessing and assessing complex high-dimensional data, allowing superior efficiency in navigating vast material configuration space in search of viable structures. Coupling such capabilities with physically significant data to construct trained models for materials discovery is crucial to moving this emerging field forward. Here, we present a universal GM for crystal structure prediction (CSP) via a conditional crystal diffusion variational autoencoder (Cond-CDVAE) approach, which is tailored to allow user-defined material and physical parameters such as composition and pressure. This model is trained on an expansive dataset containing over 670,000 local minimum structures, including a rich spectrum of high-pressure structures, along with ambient-pressure structures in Materials Project database. We demonstrate that the Cond-CDVAE model can generate physically plausible structures with high fidelity under diverse pressure conditions without necessitating local optimization, accurately predicting 59.3% of the 3547 unseen ambient-pressure experimental structures within 800 structure samplings, with the accuracy rate climbing to 83.2% for structures comprising fewer than 20 atoms per unit cell. These results meet or exceed those achieved via conventional CSP methods based on global optimization. The present findings showcase substantial potential of GMs in the realm of CSP.

深度学习生成模型 （GM） 的最新进展在访问和评估复杂的高维数据方面创造了强大的功能，从而可以非常高效地导航广阔的材料配置空间以寻找可行的结构。将这些功能与物理上重要的数据相结合，以构建用于材料发现的训练模型，对于推动这一新兴领域向前发展至关重要。在这里，我们提出了一种通过条件晶体扩散变分自动编码器 （Cond-CDVAE） 方法进行晶体结构预测 （CSP） 的通用 GM，该方法经过定制，可允许用户定义材料和物理参数，例如成分和压力。该模型在一个广泛的数据集上进行训练，该数据集包含超过 670,000 个局部最小结构，包括丰富的高压结构谱，以及 Materials Project 数据库中的环境压力结构。我们证明 Cond-CDVAE 模型可以在各种压力条件下生成物理上合理的结构，并且具有高保真度，而无需局部优化，在 800 个结构采样中准确预测了 3547 个看不见的环境压力实验结构中的 59.3%，对于每个晶胞包含少于 20 个原子的结构，准确率攀升至 83.2%。这些结果达到或超过通过基于全局优化的传统 CSP 方法实现的结果。目前的研究结果表明，GM 在 CSP 领域具有巨大潜力。