Azernews.Az

By Alimat Aliyeva

Google has introduced a groundbreaking feature in its Gemini app, enabling users to generate videos from static images, powered by the advanced Veo 3 model. This tool, which was previously exclusive to the AI Ultra subscription tier, is now also accessible to Google AI Pro subscribers for the first time, marking a significant expansion in its availability, Azernews reports, cititng foreign media.

The image-to-video tool allows users to create 8-second video clips at 720p resolution, with synced audio, all directly from an image. However, Google has set certain limitations: the video output is locked to a 16:9 landscape format, which may not be ideal for platforms like Instagram or TikTok, where vertical videos dominate.

To use the feature, Gemini users can simply select the "video" option under the "tools" menu in the app. Additionally, this feature is integrated with Google's Flow, its AI-driven filmmaking app, which has now expanded to 75 new countries, increasing its global reach. This integration helps streamline the process of turning static images into short, dynamic video content, making it easier for content creators and marketers alike to leverage AI in their workflows.

The feature is initially rolling out for desktop users, with mobile access expected by the end of the week. The AI Pro subscription, which costs $20 per month, gives users access to this image-to-video tool, while the more advanced AI Ultra plan, priced at $250 per month, offers additional features and capabilities.

What’s particularly interesting is how this could change the landscape of content creation. With AI tools like these becoming more accessible, it’s likely we’ll see a surge in creative video content from users who traditionally only created static images. This could even lead to the rise of a new wave of visual storytelling where short-form videos are made from photos or illustrations, challenging the dominance of traditional video production.