Google has introduced a new tool in its Gemini AI chatbot that converts photos into short animated videos complete with sound. Powered by the Veo 3 model, the feature lets users upload images and provide instructions for animating elements and adding audio, creating dynamic 8-second clips.
Users start by selecting the Video option in Gemini’s prompt box, uploading a photo, and then directing how the animation and sound should play out. The videos can be shared or downloaded and are embedded with a visible and invisible SynthID watermark to verify their AI origin.
This photo-to-video tool is currently available on the web, but only for Google AI Pro and AI Ultra subscribers in select countries. The subscription costs $19.99 per month for AI Pro and $249.99 per month for AI Ultra.
Extension to Google’s Filmmaking Tool
The animation capability has also been added to Google’s AI filmmaking platform, Flow, where users can animate elements and make them interact with one another.
Since Veo 3’s launch in May, Google reports over 40 million videos generated with the model. However, the technology has been misused to produce AI-generated racist videos, which have appeared on platforms like TikTok.
What The Author Thinks
While Google’s new animation tool opens exciting creative possibilities, it also underscores the critical need for responsible AI governance. As these technologies grow more accessible, ensuring safeguards against misuse and harmful content is vital for maintaining trust and protecting users.
Featured image credit: TipRanks
For more stories like it, click the +Follow button at the top of this page to follow us.