Google appears to be preparing a more advanced way to bring photos to life within its Photos app, hinting at a deeper integration of generative AI tools. Hidden traces of upcoming functionality have been discovered, suggesting users may soon be able to transform still shots into video clips through typed commands instead of relying on preset animations.
| Image credit: StarklyTech
- Google Photos may soon let users turn still images into videos using typed AI text prompts.
- Hidden code hints at a new photo-to-video feature powered by generative AI in Google Photos.
- The update could replace preset animations with customisable text-based effects for more creative control.
- Google’s AI ecosystem continues to expand, linking Photos, Gemini, and smart home devices under one vision.
- With rivals like OpenAI’s Sora advancing fast, Google’s upcoming photo-to-video tool signals growing AI competition.
Google appears to be preparing a more advanced way to bring photos to life within its Photos app, hinting at a deeper integration of generative AI tools. Hidden traces of upcoming functionality have been discovered, suggesting users may soon be able to transform still shots into video clips through typed commands instead of relying on preset animations.
This new system, referenced in the latest app code, points to the introduction of a full text prompt box. That means instead of choosing between basic options, users will be able to describe what kind of movement, transition, or effect they want applied to an image. Such flexibility could make the photo-to-video experience far more creative and personalised than before, giving users more control over the outcome.
At present, only limited choices exist for this feature — such as 'subtle movement' or 'I'm feeling lucky' — both of which leave most of the decision-making to Google's algorithms. The enhanced version seems ready to replace that simplicity with customisable animation prompts, allowing users to shape their media precisely how they envision it.
Powering this upgrade is the older Veo 2 model, which has been used in Google Photos for a while. Despite not being as powerful as the latest Veo 3 engine, it’s still able to produce lively, realistic results from a single static frame. The new feature may serve as a testbed for Google to refine the model further before moving to more sophisticated versions in future updates.
This push fits into Google’s wider goal of spreading AI capabilities throughout its ecosystem. From Gemini assistants embedded in smart home gadgets to the evolving suite of creative tools in its core apps, the company continues to expand its AI footprint beyond simple search and productivity features.
Its strategy also extends to hardware. The recently revealed Nest cameras and upcoming smart speaker have AI deeply integrated, ensuring that devices across the Google lineup benefit from the same neural processing improvements being rolled out on mobile platforms.
Competitors aren’t standing still either. OpenAI’s ongoing rollout of Sora 2, a text-to-video platform paired with a lightweight social hub, underscores how quickly this segment is heating up. There are even whispers of new hardware under the ChatGPT brand, showing that the rivalry between these AI giants is intensifying.
Whether Google decides to make this hidden feature public remains to be seen. But given the company’s track record of gradually turning test features into permanent updates, there’s a strong chance this creative image-to-video tool will quietly appear in a future Photos release. For now, users will just have to watch for hints in upcoming versions of the app as Google’s AI-powered creativity tools continue to evolve.