Google's Gemini AI has new photo to video functionality

AI Video & Visuals


A green alien with big black eyes is seen in an open cardboard box on the table in the home environment.
Photo-to-video functionality allows users to turn normal scenes into extraordinary scenes.

Google has launched a new feature within the Gemini AI Assistant, which allows users to convert photos into short video clips, expanding access to tools that are previously limited to Flow, a standalone film production platform.

With Gemini Advanced Subscrivers available on Ultra and Pro plans in certain regions, this feature will begin rolling out on Thursday and arrives on mobile devices throughout the week. Users can upload images and generate 8-second video based on accompanying text and audio prompts. The clip includes AI-generated sound effects, ambient sounds and sounds, and is delivered in MP4 format at 720p resolution with a 16:9 landscape aspect ratio.

The tool is powered by Google's VEO 3 AI video model and was first announced in May. Users can access the feature by selecting the “Tools” option in the Gemini interface, selecting “Video” and uploading a photo that describes its movement. You can also add audio inputs for synced dialogs and sound effects.

“You can increase your creativity by animating everyday objects, bringing drawings and paintings to life, and giving natural scenes movement,” Google said in a blog post. All generated videos include visible watermarks that indicate that they were created with AI, and invisible SynthID digital watermarks.

Bloomberg With the new integration, Gemini is approaching similar offerings from competitors such as Openai, Runway AI and Pika, as well as Chinese companies, including Alibaba and Kuaishou, who have developed AI video tools.

The cursor covers hovers "Add a photo" Dark interface button with tooltip "Turn your photos into videos." Beside it is a photo of a toy rocket with blue fins and red cone.

Although this feature is based on features already available in Flow, Gemini now offers a more accessible, chat-based experience. According to Google, Flow itself has also expanded availability and is now available in 75 more countries.

The company highlighted safeguards aimed at preventing misuse of video generation tools. Restricts the use of public figures' images and prohibits output that promotes harmful or violent content. However, technology is still developing. Google says the technology is now more effective at animating non-human subjects, such as plants, animals and artwork.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *