Apple is working on AI models for image and video generation


Apple, known for its tech innovations, is delving into AI research. They've introduced a novel approach to generating high-quality images and videos using a Multi-Resolution Diffusion Model (MDM). What's intriguing is that this model doesn't require a pre-trained VAE (Variational Autoencoder), making it more efficient than conventional models like Stable Diffusion XL. It's a sign that Apple is taking AI seriously, even if their involvement is somewhat shrouded in mystery. Their research shows promise in generating high-quality images and videos, making their mark in the AI art generation space.


Post a Comment

Previous Post Next Post