Google is preparing to expand its AI-powered tools in Google Photos, and new features specifically allow users to turn still images into short videos.
The new AI feature in Google Photos is particularly described as revolutionizing conventional editing, powered by the Gemini AI model.
This will enable users to describe the type of of animation they want and give them more creative control than before.
The upgraded feature is expected to run on Google’s Veo 2 model, which is considered an older but powerful video-generation system.
The model retains the ability to produce visuals and animated sequences from a single image.
Users primarily don't need advanced tools so that a single photo can bring a moment to life.
The new feature is part of Google’s broader strategy to embed AI technology across several applications and devices.
The company is increasingly working to expand its range of models from Gemini integrations in Gmail and Docs to AI-powered Nest cameras and upcoming Google smart speakers.
The remodelling of applications plays a crucial role in making Google’s ecosystem more integrated and providing its AI tools an edge over giants like ChatGPT and Sora 2.
OpenAI is playing a central role in expanding its wide variety of products. The company has introduced Sora 2, which is an advanced version of a video application with a social networking layer.
The two tech giants are racing to redefine users' daily interactions with AI and create innovation tasks like image animation and media creation.
Currently, no official timeline has been released by Google, and the project is in the preparatory phase.
Users have to wait to experience a richer and customizable photo animation experience directly within Google Photos.