Google has announced the expansion of its advanced video loo model, VEO 3, making it available to Google AI Pro subscribers in over 150 countries, including Pakistan.
This roll-out, which was announced in a press release on Friday, introduces a powerful new photo-to-video feature that allows users to immediately transform still images into live, eight seconds video clips complete with audio.
The new capacity is built on the basis of VEO 3, launched earlier this year. Integration allows users to utilize Google’s advanced AI to breathe life into their favorite photos and offer a trouble -free way of creating engaging visual content.
Globally, users have already created over 40 million VEO 3 videos in just seven weeks – recovering adventure, experimenting with ASMR and pushing the boundaries of creativity.
Pakistan’s growing community of digital storytellers and content creators can look forward to exploring these opportunities.
How to use the new VEO 3 feature?
To transform photos into videos, select ‘Videos’ in the tool menu in the prompt box and upload a photo. Then describe the stage and any audio instructions, and watch as the image is transformed into a dynamic video.
Now available to Google AI Pro and Ultra subscribers in selected countries, this tool allows users to animate everything from personal moments to creative sketches.
Just upload a photo, describe the stage and any sound signals, and Gemini generates a dynamic video for download or sharing. These options are also available in flow, Google’s AI film creation tool.
Expansion of creative options in flow
Users can also explore these features of flow, Google’s AI tools for filmmakers, which now allows adding speech to video clips along with sound effects and background sounds. However, sound generation in flow is still experimental, so the results can vary.
Frames for video – which lets personal images become the starting point for dynamic clips – are also available on VEO 3 quickly, which helps users get even more from their credits. Flow and Google AI Ultra are now available in over 140+ countries and are expanding access to these groundbreaking creative tools.
Ensuring confidence, security in AI
Google is obliged to responsible AI. All videos generated with Gemini include a visible watermark and an invisible synthid digital fields to indicate that they are AI created.
The company also performs extensive “red teaming” exercises to proactively test its systems, identify and solve potential problems before they arise, and perform thorough evaluations to understand how these tools can be used and how abuse can be prevented.
Policies against uncertain content are continuously enforced and user feedback is actively sought to further strengthen security measures.
Use the thumbs up and down on the buttons on generated videos for feedback, which will be used to make continuous improvements to the security measures and the overall experience.
