Google is also launching Flow, the only AI filmmaking tool custom-designed for Google’s most advanced models — Veo, Imagen and Gemini. Flow can help storytellers explore their ideas without bounds and create cinematic clips and scenes for their stories. 

Photo-to-video brings images to life

To turn photos into videos, select ‘Videos’ from the tool menu in the prompt box and upload a photo. Then, describe the scene and any audio instructions, and watch as the selected still image transforms into a dynamic video. Users can get creative by animating everyday objects, bringing their drawings and paintings to life or adding movement to nature scenes. Once the video is complete, users can tap the share button or download it to share with friends and family.

Flow: available in MENA & in Arabic

Flow comes with a range of features for professionals or those just getting started:

• Camera Controls: Master some shots with direct control over camera motion, angles and perspectives.
• Scenebuilder: Seamlessly edit and extend existing shots — revealing more of the action or transitioning to what happens next with continuous motion and consistent characters.
• Asset Management: Easily manage and organize all of the ingredients and prompts.

The explosion of creativity from users has been truly remarkable, with over 40 million Veo 3 videos generated across the Gemini app and Flow over the last seven weeks. All generated videos include a visible watermark to show they are AI-generated and an invisible SynthID digital watermark.

Users can access Gemini, and check the Google AI Pro and Ultra subscriptions to explore Veo 3 and Flow, Google’s AI filmmaking tool. 

With Veo 3 now built into the Gemini app, people can write the scene they want to watch. This description is called a “prompt” and with it, Veo 3 will whip up a custom eight-second video complete with sound, dialogue and music, at 720p output.  

Veo 3 was released at Google’s annual event for developers, Google I/O, last May. Veo 3 lets users add sound effects, ambient noise, and even dialogue to their creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.

The SynthID watermark is embedded in all content generated by Google’s generative AI models, including Veo 3. Google recently rolled out SynthID Detector to early testers, and aims to expand access soon. As an additional step to help people identify AI-generated content, a visible watermark will be added to all videos generated by the video model, except for videos generated by Ultra members in Flow, Google’s latest tool for AI filmmakers.

People can subscribe to Google AI Pro to try out Veo 3, starting today.