Google’s New Photo-to-Video AI Just Made Creativity a Lot More Fun

Anzalna Siddiqui

A psychology major in her third year of Bachelor’s, Anzalna Siddiqui has endless curiosity for the human mind and a deep love for storytelling – both through words and visuals. Though she hasn’t taken up photography as a profession, her Instagram is where her passion finds its home. In addition to this, she’s a travel enthusiast who never travels without her camera because every place has a story waiting to be captured.

Photo-to-Video AI

There is something fun about bringing a still picture to life. Now, Google’s Gemini platform makes it possible surprisingly easily. Their new photo-to-video AI tool allows you to take any photo and convert it into an eight-second video clip, with audio.

The feature was rolled out in silence to Google AI Pro and Ultra subscribers last week. You can upload your own image, tell the scene, indicate the type of sound you would like, and see the AI construct a moving form of your picture. It can be a landscape, a sketch, or even a random household item.

To me, stop motion and imagination combined, driven by a neural engine. No editing software or animation expertise required. Just an idea.

What Sets This Photo-to-Video AI Tool Apart from Others?

The figures are sort of wild. Veo 3 creators have produced over 40 million videos in the last seven weeks on Gemini and Flow, Google’s AI filmmaking software. That is a lot of creativity, particularly for a feature still being rolled out.

Already, people are using the tool in ways not anticipated. Taking silent moments and making them into mini-videos. Redoing fairy tales. Making ASMR-esque soundscapes. Google assures us the only limitation is your imagination, and sounding real, that does not sound like marketing hype this time.

Behind the scenes, Google claims to be considering safety very seriously. The tool has visual and invisible watermarks to indicate that the content is AI-generated. Their teams are stress-testing the tool to avoid abuse. There are even thumbs-up and thumbs-down buttons to provide feedback on results.

It is too early and only available for subscribers in specific countries. But the trend is apparent. This photo-to-video AI tool may revolutionize what we consider a photo can be.

I used it on a peaceful forest image and requested soft wind noises and falling leaves. The outcome stunned me. Not only did it appear nice, but it also seemed to breathe. Features such as this remind me why I enjoy being in this changing space. There is always something new to find out, even in one static picture.

[via Google; Image credits: Google]


Filed Under:

Tagged With:

Find this interesting? Share it with your friends!

Anzalna Siddiqui

Anzalna Siddiqui

A psychology major in her third year of Bachelor’s, Anzalna Siddiqui has endless curiosity for the human mind and a deep love for storytelling – both through words and visuals. Though she hasn’t taken up photography as a profession, her Instagram is where her passion finds its home. In addition to this, she’s a travel enthusiast who never travels without her camera because every place has a story waiting to be captured.

Join the Discussion

DIYP Comment Policy
Be nice, be on-topic, no personal information or flames.

Leave a Reply

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