Google's Veo 3.1 can turn separate images into a single video
Google DeepMind's Veo 3.1 blends multiple still images into realistic videos with synchronized audio, offering improved realism, storytelling understanding, and a faster variant.
OpenAI releases Sora 2 video model with improved realism and sound effects
Sora 2 generates realistic, physically accurate videos with improved audio, editing controls, scene consistency, safety safeguards, an iOS app, and initial free US/Canada access.