Google Upgrades Veo 3 With New Image-to-Video Feature

Google has announced a new image-to-video generation feature for its Veo 3 AI video generator, now available through the Gemini app. Previously, this function was introduced in Google’s Flow tool, launched in May during the company’s I/O developer conference. Following the debut of Veo 3-powered video creation in May, Google has made the feature accessible in over 150 countries as of last week.  However, at this stage, only subscribers to the Google AI Ultra and Google AI Pro plans can use the image-to-video tool, with a limit of three video creations per day that does not roll over if unused. To create a video using this feature, users simply select the “Videos” option from the tool menu within the prompt box and upload their chosen photo. They can further personalize the clip by describing the desired audio, which will then be added during the video generation process. Once completed, users have the option to download their video or share it with others.  Since the feature’s release just seven weeks ago, Google reports that more than 40 million videos have been created through the Gemini app and Flow tool combined. To help viewers and platforms recognize AI-generated content, every video produced with the Veo 3 model contains two types of watermarks: a visible label reading “Veo” and an invisible SynthID digital watermark. The SynthID technology, adopted by Google, allows digital artifacts made by AI tools to be identified reliably. Google’s addition of image-to-video generation to Veo 3 reflects the company’s ongoing efforts to expand creative capabilities with artificial intelligence while promoting transparency in how AI-generated content is made and shared. With this update, Google continues to offer new tools for users to experiment with visual media, pushing the boundaries of what AI-powered video generation can achieve.