Google Photos today unveiled Video Remix, a generative‑AI feature that can transform video clips in seconds. Accessible through the app’s Create tab, the tool leverages Google’s latest Gemini Omni model – a multimodal engine that promises to “create anything from any input.”

How the feature works

With Video Remix, users can brighten a dimly lit clip using cinematic relighting, replace a plain backdrop with a greenhouse or a playful scene, and overlay artistic filters such as watercolor, raw sketchbook, or oil‑painting effects. The workflow is deliberately simple: select a video, choose a style, and let the AI render the transformation in real time.

Technical backbone

Gemini Omni, Google’s newest large‑scale model, powers the tool. Trained on massive multimodal datasets, the model can interpret visual cues, generate realistic lighting adjustments, and synthesize new backgrounds while preserving motion continuity. This depth of understanding enables the seamless, near‑instantaneous edits that were previously only possible with dedicated desktop software.

Competitive landscape

The launch arrives as Apple, OpenAI, Adobe and other tech giants race to embed generative AI into consumer products. By embedding Video Remix directly into Google Photos, the company reduces friction for users who would otherwise need separate video‑editing applications. The move also strengthens Google’s ecosystem, encouraging users to stay within its cloud‑first suite of services.

User impact and rollout

Video Remix is rolling out today to eligible Google AI Plus, Pro, and Ultra subscribers across the United States, Argentina, Bangladesh, Brazil, Colombia, Egypt, India, Indonesia, Japan, Mexico, Pakistan, the Philippines, South Korea and Turkey. The feature promises to democratise video editing, turning ordinary clips into share‑worthy moments without hours of manual work.

Future outlook

Google Photos has already added AI‑driven touch‑up tools, a digital wardrobe feature, and now Video Remix, signalling a broader strategy to embed AI across its consumer portfolio. As Gemini Omni evolves, we can expect even more nuanced control—perhaps real‑time scene synthesis or adaptive storytelling—further blurring the line between casual creators and professional editors.