Google's artificial intelligence (AI) chatbot has added a new feature to Jemini. Now users can make an eight second video with only one picture-it is again with words!
This facility has been launched in Google's advanced video model with the name 'VO3'. It will make the video as per the picture description and direction of the image, not just the picture.
However, Jemini's new feature has been launched in certain areas for Google AI Ultra and Pro subscribers. However, the feature is currently available in the web version of Jemini and will slowly launch Jemini's mobile version, Google said.
Gamine users can select 'Video' by clicking on the Prompt Bar's 'Tools' option and uploading the picture. Then the instructions will be given through the text. For example, how to move inside the image and what kind of sound will be. If desired, the background sound, the sound of the environment or the conversation can also be added as instructions.
The videos created can be downloaded in the MPFor (MP3) format, 1: 1 landscape and 120p resolution. Each video will have an visible and an invisible 'SyntID Watermark' (watermark), which will inform an AI-generated content.
Google says, “This feature can be used to add animation to everyday objects, to alive your own paintings or to speed up the scene of nature.”
Significantly, in March this year, Google launched a general filmmaking tool called 'Flow', where there was the advantage of making video from similar pictures. But this time it can be done directly through Jemi, no one has to open a separate app.
Google also said that the feature called Flow is being launched in five more countries.
References: The Verge
