Google adds photo-to-video generation with Veo 3 to the Gemini app

Since its launch in May, Google's Veo 3 has been making waves online, merging reality with imaginative visuals. The latest update to the Gemini app enhances this experience by introducing a photo-to-video feature, allowing users to effortlessly convert images into dynamic videos. This innovative functionality is accessible to subscribers of Google's Pro and Ultra AI plans, adding no additional costs for the creation of Veo 3 videos. Initially, Veo 3 could generate videos solely from user descriptions, including synchronized speech, music, and background sounds, resulting in remarkably lifelike AI-generated content that can be challenging to distinguish from real footage. With the new photo-to-video capability, users can simply upload a reference image to achieve the desired visual style without the hassle of intricately detailing every element. Previously available in Google's Flow AI tool tailored for filmmakers, this feature has now made its way into both the Gemini app and web platform. To start the video creation process, users need to select the 'Video' option from the Gemini toolbar. After adding their chosen image along with prompts for audio and dialogue, the video generation process begins, typically taking several minutes due to the significant computational resources required. However, the current output of videos remains somewhat limited as the technology continues to evolve.