Translated data: Apple has recently unveiled the Matryoshka Diffusion Model (MDM) for generating high-resolution images. This model employs a nested UNet architecture and multi-resolution loss, enhancing both the efficiency and quality of image generation while circumventing the need for complex cascading or latent diffusion methods. Experiments have demonstrated the MDM's robust capabilities in zero-shot generation, offering a more efficient and high-quality solution for generative AI applications, and is expected to drive the advancement of the generative AI field.