MobileDiffusion: Rapid text-to-image generation on-device

Posted by Yang Zhao, Senior Software Engineer, and Tingbo Hou, Senior Staff Software Engineer, Core ML

Text-to-image diffusion models have shown exceptional capabilities in generating high-quality images from text prompts. However, leading models feature billions of parameters and are consequently expensive to run, requiring powerful desktops or servers (e.g., Stable Diffusion, DALL·E, and Imagen). While recent advancements in inference solutions on Android via MediaPipe and iOS via Core ML have been made in the past year, rapid …

capabilities computer vision core dall desktops diffusion diffusion models engineer feature image image diffusion image generation imagen images machine learning on-device learning parameters prompts quality servers software software engineer stable diffusion staff text text-to-image yang