Essential information
- Google has outlined the launch of photo-to-video generation features in Gemini, powered by Veo 3.
- Users have the ability to upload an image and provide a comprehensive text description detailing how they wish Gemini to produce the video, complete with distinctive sounds if they choose.
- This similar function was introduced by Google Cloud to Honor’s 400 series earlier in the year with Veo 2.
Google is introducing a robust new AI-generation feature in its Gemini app today (July 10) to enhance your memories.
In a post on Keyword, Google announced the debut of photo-to-video generation features within the Gemini app. The company informs that users with a Google AI Pro or Ultra subscription can select the “Video” option in the prompt box and upload a photo. On a corresponding support page, Google mentions that users can then enter a text description into the box to guide the AI on how they wish the video to be created.
The announcement advises users to be as detailed as possible, explaining the scene and “any audio guidelines” for Gemini. Upon completion, users should scroll down beneath the text box to More