Google said Thursday it was adding image-to-video generation capabilities to its VEO 3 AI video generator via the Gemini app.
The company had already deployed the feature in an AI-powered video tool called Flow, which was launched at Google's I/O Developer Conference in May.
After starting video generation with VEO 3 in May, Google made the feature available in over 150 countries last week. At the moment, only Google AI Ultra and Google AI Pro Plan users can generate videos with a limit of 3 creations per day without carrying over.
Image to video generation using VEO 3 looks like IMAGE credits: Google
Google said users can generate clips by uploading photos by selecting the “Video” option from the Tools menu in the prompt box. You can also add sounds by explaining the audio at the prompt. Once the video is generated, it can be downloaded or shared with others.
The company said that since its release seven weeks ago, users have created over 40 million videos across the Gemini app and Flow tool. All videos generated using the VEO 3 model have a visible watermark formula with “VEO” written along with “VEO”, and is used by AI tools that Google's AI tools can identify digital artifacts powered by AI.
Earlier this year, the company also released a tool that helps detect content that includes SynthID.