Google Photos adds Video Remix: AI edits powered by Gemini
Video Remix, powered by Gemini Omni, starts rolling out to eligible Google AI Plus, Pro and Ultra subscribers.
TL;DR
- 01Video Remix, powered by Gemini Omni, starts rolling out to eligible Google AI Plus, Pro and Ultra subscribers.
- 02Google Photos is getting a new "Video Remix" feature that can edit and transform videos in seconds, powered by Gemini Omni, Google announced on Wednesday.
- 03Google offered concrete examples of the edits: you could make a clip look as if it were shot in a greenhouse, relight footage with a morning glow, or render video in a watercolor effect.
Google Photos is getting a new "Video Remix" feature that can edit and transform videos in seconds, powered by Gemini Omni, Google announced on Wednesday. The tool is available starting today to eligible Google AI Plus, Pro and Ultra subscribers in the U.S., Argentina, Bangladesh, Brazil, Colombia, Egypt, India, Indonesia, Japan, Mexico, Pakistan, Philippines, South Korea and Turkey.
What is Video Remix and how does it work?
Video Remix is a new editing tool inside Google Photos that applies generative AI to short clips, performing tasks such as cinematic relighting, background swaps and stylistic conversions in a few taps. Users access the tool from the Create tab in Google Photos and can apply effects described in the announcement, including cinematic relighting to brighten a dark clip, replacing a plain background, and adding artistic looks such as watercolor, raw sketchbook, and oil painting.
Google offered concrete examples of the edits: you could make a clip look as if it were shot in a greenhouse, relight footage with a morning glow, or render video in a watercolor effect. The underlying model is Gemini Omni, which the announcement ties to the feature as the powering generative model for these transformations.
Who gets Video Remix and where is it available?
Video Remix begins rolling out to eligible Google AI Plus, Pro and Ultra subscribers, and the company listed the initial availability across the U.S., Argentina, Bangladesh, Brazil, Colombia, Egypt, India, Indonesia, Japan, Mexico, Pakistan, Philippines, South Korea and Turkey. The feature shows up in the Photos app under the Create tab, so subscribers with the updated app should see the option when editing clips.
The announcement positions Video Remix as an addition to a recent string of AI updates in Google Photos. The app previously gained new touch-up tools for photos that let users remove blemishes, refine skin texture, brighten eyes and whiten teeth. Google also introduced an AI-powered feature that turns photos of clothes into a digital closet for creating outfit ideas and virtually trying on looks.
Why it matters
Video Remix lowers the barrier to producing stylized or corrected video clips by moving those capabilities into a consumer photo app rather than leaving them to dedicated editing software. Google framed the feature around ease of use, writing, "Creating beautiful video clips shouldn’t require professional skills or hours of editing." Embedding Gemini Omni-powered edits inside Photos also reinforces Google’s strategy of folding generative AI into core consumer products as it competes with companies like Apple, OpenAI and Adobe.
That matters for two groups: casual users who want faster, point-and-shoot ways to improve clips, and Google itself, which gains another reason to keep users inside its ecosystem by offering edits that previously required separate apps or desktop software.
What to watch
Watch whether Google expands Video Remix beyond the initial subscriber tiers and markets, and whether the company adds deeper controls or longer-clip support over time. Also look for how Google connects Video Remix to other Photos features, and whether similar quick-edit AI tools start appearing from competitors named in the announcement.
"Creating beautiful video clips shouldn’t require professional skills or hours of editing," Google wrote in its blog post about Video Remix. Expect the rollout, and subsequent user feedback, to shape how aggressively Google surfaces generative video edits elsewhere in its consumer products.
Written by The Brieftide · Source: TechCrunch
The Brieftide Daily · 06:00
Briefs like this one, in your inbox every morning.
Continue reading
More in Multimodal AIBRAID: Unified RL for Interleaved Multi-Modal Reasoning
A July 4, 2026 arXiv paper frames text-image-text reasoning as a single MDP.
MMIR-TCM: multimodal TCM AI framework outperforms GPT-4o, Gemini
MMIR-TCM pairs Memory-SAM, fine-tuned Qwen3-VL and a Qwen3 RAG pipeline.
MIT Masked IRL: LLMs help robots clarify and ignore cues
MIT’s Masked IRL uses two LLMs to clarify vague prompts, cut demonstration data nearly fivefold.
Multimodal LLM evaluation: four missing capabilities (2026)
A paper by Po-han Li et al. finds benchmarks miss temporal-spatial coherence, physical-world understanding.