The self-developed AI visual large model by Meitu, MiracleVision, has released version 4.0, introducing two new capabilities: AI Design and AI Video. AI Design encompasses four main features: vector graphics, text effects, smart layering, and intelligent typesetting. Users can quickly generate vector graphics that match their design style, customize text effects, identify and convert objects into independent layers, and conduct typesetting designs for text and images through natural language interaction. MiracleVision 4.0 also introduces a brand new visual model store, where users can select different visual models to create various unprecedented effects. The AI Video capability includes four main functions: text-to-video, image-to-video, video tracking, and video-to-video. Users can generate natural and smooth videos by inputting prompts, bring images to life, simulate professional camera movements, and even add different artistic styles to existing videos. The video generation capabilities of MiracleVision 4.0 have been integrated into the workflows of the e-commerce and advertising industries, particularly suitable for creating product showcases and brand advertisements, enhancing visual effects.