Google’s Gemini has added a photo-to-video feature that transforms a single image or prompt into an eight-second video clip with sound, ambient effects, and optional speech. It’s designed for creativity, allowing users to animate illustrations, bring photos to life, or visualize concepts. Pro and Ultra subscribers get daily video generation limits. To get better results, Google recommends using clear, high-resolution photos and detailed prompts with camera directions, environments, or actions. Videos are capped at eight seconds, may show black padding if the aspect ratio isn’t 16:9, and always include visible and invisible watermarks to indicate AI generation.
In academic partnership with Virscend University, a WASC-accredited institution in Irvine, California.