Google’s recent update to the Gemini AI platform introduces an innovative photo-to-video feature, enabling users to turn still images into dynamic eight-second video clips with sound. This capability utilizes Veo 3, Google’s cutting-edge video generation model, now accessible to Google AI Pro and Ultra subscribers in over 150 countries. David Sharon, Multimodal Generation Lead, emphasizes the ease of creating videos by selecting ‘Videos’ in the tool menu, uploading a photo, and providing scene descriptions and audio prompts. Since its launch, over 40 million Veo 3 videos have been generated, showcasing diverse creative applications from storytelling to ASMR experiences. Veo 3 also serves enterprise needs via Google Cloud Vertex AI, facilitating rapid content creation for businesses. Google prioritizes responsible AI development, incorporating safety measures like visible watermarks, user feedback systems, and thorough evaluations to ensure safe usage. The rollout of this feature marks a significant advancement in AI-driven creative tools.
Source link
