As of: 2026-11-13 13:49 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/v/introducing-gemini-omni-google/ # Introducing Gemini Omni: Create Anything from Anything Google, 19 May 2026, YouTube. 26,045,325 views as of 9 October 2026. Kind: Official. Watch: https://www.youtube.com/watch?v=KUyRq7szZsM ## Description (written by Gemini from the video) **Summary** This is an official promotional video produced by Google DeepMind showcasing the creative and generative capabilities of "Gemini Omni." Set to an upbeat instrumental track with no spoken voiceover, the video demonstrates multimodal video generation, real-time style transfers, scene modifications, and world building. **What is shown** - [00:00] Title card displaying "Gemini Omni" over natural spiral patterns (sunflower, chameleon tail, snail shell). - [00:03] Text overlay "Create anything / From everything" displaying floating modality icons (audio, images, video, text prompts, 3D objects). - [00:06] Video-to-video transformations of a man in front of a mirror: blowing fire, generating water ripples by touching glass, and transforming into a felt puppet, hand-drawn comic sketch, and voxel/block character. - [00:14] Text "Look what you can do" across rapid scenes including a first-person whitewater kayak run, Martian landscape traversal in a space suit, a water slide, a desert stagecoach chase, and an animated pop-up sci-fi book. - [00:19] Text "Build worlds" displaying material and structural swaps on a sculptural pavilion (illuminated patterns, yarn/knit texture, flower arches, foam bubbles) and liquid metal physics. - [00:28] Motion-guided generation showing a drawn path that a 2D clownfish follows before leaping out of water into a realistic seascape. - [00:31] Interface combining multimodal assets into a sci-fi scene, followed by contextual element editing: "Swap character" (astronaut replaced by a giant fish), "Swap detail" (space station ring replaced by flying origami cranes), "Swap style" (comic book line art), "Swap environment" (jungle planet canopy), and "Swap angle" (first-person helmet reflection). - [00:42] Montage of diverse scenes including bio-architecture interiors, a lunar dome colony, skate video overlays ("POW!" comic effects), and UFOs descending over clouds. - [00:48] Closing title cards displaying "Gemini Omni" over a black hole accretion disk and the "Google DeepMind" logo. **Claims & numbers** - None (the video contains no spoken claims, release dates, pricing, or quantitative benchmarks; on-screen copy consists solely of feature labels and promotional taglines). **Notable quotes** - [00:03] *"Create anything / From everything"* (on-screen text) - [00:14] *"Look what you can do"* (on-screen text) - [00:36] *"Swap character / Swap detail / Swap style / Swap environment / Swap angle"* (on-screen text) **Assessment** This is an official promotional teaser reel from Google DeepMind. The footage presents highly polished, cherry-picked visual outputs and conceptual editing capabilities rather than raw, unedited real-time interaction in an end-user UI. _Described by gemini-3.8-flash on 2026-09-29 from the video's audio and frames._ ## How AI was used to make it AI made most of it of this video (Generated footage). - Multimodal video generation and video-to-video style transfers - Motion-guided video generation and scene editing Tools: Gemini Omni (Classified by gemini-3.8-flash from our description; high confidence. Overview: https://postcutoff.com/ai-video/) ## Related - 2026-05-19: [Google unveils Gemini Omni, an any-to-any model that generates and conversationally edits video](https://postcutoff.com/e/2026-05-19-gemini-omni/) ## More videos on this - 2026-05-19: [Introducing Gemini Omni](https://postcutoff.com/v/introducing-gemini-omni-google-for-developers/), Google for Developers, YouTube, official, 18,326 views as of 9 October 2026. What else happened that month, day by day: https://postcutoff.com/timeline/2026/05/