YouTube Shorts and Google Photos have a new ability: converting still images into video. This week, Google unveiled several key updates to YouTube Shorts and Photos that use generative AI. The update gives users on both platforms the ability to turn still photos into short video clips using generative AI, along with adding a handful of other AI-based tools.
Google Gemini already had the ability to create a video from a photo, a feature that has already rolled out earlier this month. But that AI capability is now coming to YouTube Shorts and Google Photos.
Photo to video capability inside Google Photos and YouTube Shorts
For both YouTube Shorts and Google Photos, the user selects a photograph, then chooses from one of the prompt options. Those AI prompts are pre-suggested rather than written out by the user.
In Google Photos, the feature launches with two options: “Sutble movements” or “I’m feeling lucky.” Google says that photos of people work best for the new tool.
For YouTube Shorts, the feature launches with the ability to add movement to landscape photos, animate “everyday photos,” or turn group photos into videos.
Looking at the example Google shared to announce the feature on YouTube Shorts, there are a few telltale AI signs. The text on a flyer from the still photo turns to gibberish in the video, and the photo on the same flyer flickers in the generation, while the pole the flyer is on isn’t perfectly straight.
The examples of the tool in action on Google Photos seem to animate people in a celebratory mood, in two examples having them throw confetti, and in another releasing balloons into the air.
On Google Photos, the screenshots show a subtle warning: Experimental GenAI: results may be unexpected.”
“These features are experimental,” Josh Sassoon, the Director of UX for Google Photos and Google One, wrote in a blog post, “and we know some outputs may not be exactly what you expect or may even be inaccurate. Use the thumbs up and down buttons on your generated images and videos to give us feedback, which we'll use to make ongoing improvements to our safety measures and overall experience.”
While Gemini uses Veo 3 to power the still-to-video tools, both Photos and YouTube Shorts use the older Veo 2. Google says that Veo 3 capabilities will be coming to YouTube Shorts later this summer.
On Google Photos, the photo-to-video tool has already started rolling out in the US on Android and iOS devices. For YouTube Shorts, the feature is rolling out over the next week in the US, Canada, Australia, and New Zealand; Google says additional regions will come later this year.
YouTube Shorts is also getting an AI Playground, new generative effects
Along with the photo-to-video capabilities, YouTube Shorts will also gain new generative effects and a dedicated space to play with generative AI called AI playground.
Generative effects allow users to play with preset AI effects, which include anything from turning a selfie video of a walk down the street into a dive into the pool to turning drawings into images. Google says these effects will be “constantly refreshing,” so the different options will update regularly. The feature is expected to roll out in the coming weeks.
Shorts’ new AI playground will house the AI creation tools in one spot. The AI playground is accessed by navigating to Create, and then tapping on the sparkle icon. This new section of YouTube Shorts will house the AI creation tools as well as inspiration and pre-written prompts and can be used to generate videos, images, and music.
Google Photos gains a new AI Remix and Create tab
Inside Google Photos, the app will soon gain an AI Remix tool. Remix, which Google says is rolling out in the coming weeks for US users, takes a photo and generates a version from a pre-selected style, like comics and sketches.
Beginning in August, Google Photos will also get a dedicated tab called Create. This tab will house the new generative AI tools as well as the options to create collages and highlight videos.
Google says that, for both Photos and YouTube Shorts, generative AI will include a SynthID watermark that flags the work as an AI creation.
You may also like
Browse the best photo organization software. Or, brush up on how to spot an AI-generated image.
You must confirm your public display name before commenting
Please logout and then login again, you will then be prompted to enter your display name.
