Google’s Veo 3 video generation model has been enhanced with image-to-video capabilities. This new feature, announced on Thursday, allows users to upload images and generate corresponding videos. Currently accessible through Gemini’s web interface, this function is not yet available on mobile apps.
Google is rolling out this feature in select countries, although the specific locations have not been disclosed. By integrating image input, Veo 3 expands its creative potential, enabling users to translate still images into dynamic video content. This update marks a significant step in improving the versatility and accessibility of AI-powered video creation.








