Google adds photo-to-video generation with Veo 3 to the Gemini app
Briefly

Since its launch in May, Google's Veo 3 has made creating AI-generated videos increasingly accessible, challenging the distinction between reality and fabrication. The Gemini app now features photo-to-video functionality, allowing users to upload images and generate videos without extra costs for Pro and Ultra subscribers. Originally, Veo 3 required only descriptive input to create videos with speech and music, but the new option simplifies the process by using reference photos, although computation limits remain for video output generation.
Google's Veo 3 videos have blurred the line between truth and fiction, allowing users to create remarkably realistic AI-generated videos by simply describing content.
The Gemini app has introduced photo-to-video generation, enabling users to upload a photo and transform it into a video without additional fees for certain subscribers.
Read at Ars Technica
[
|
]