Google has unveiled a new feature in Veo 3, part of its Gemini AI suite, that enables users to generate eight-second video clips from static images.
This innovative tool, which also supports audio, is now available to Google AI Pro and Ultra subscribers in select countries, including Pakistan.
How It Works
To use the feature, users simply select the “Videos” option from the tool menu in the prompt box. After uploading an image, they can provide a description of the scene and specify any desired audio elements. The system then produces an eight-second video complete with sound, based on the input. Users can download or share the final video directly from the platform.
To ensure transparency, each AI-generated video includes both a visible watermark and an invisible SynthID digital watermark. Users are also encouraged to provide feedback through thumbs-up or thumbs-down ratings, which helps Google enhance the feature.
Safety and Oversight
Google employs robust safety protocols, including extensive “red teaming”—a process of stress-testing systems to identify vulnerabilities—and comprehensive evaluations to assess usage patterns and prevent potential misuse. The company maintains strict policies against unsafe content and actively seeks user feedback to reinforce its safety mechanisms.
This image-to-video capability is also integrated into Flow, Google’s AI-powered filmmaking tool. According to Google, over 40 million videos have been created using Veo 3 and Flow in the past seven weeks. The addition of this new functionality is expected to further boost the platform’s adoption.
Follow us for more updates.
Leave a Reply