--- title: "I Didn’t Know AI Could Do THIS" url: https://daily.dev/posts/i-didn-t-know-ai-could-do-this-mipeyenrw source_url: https://www.youtube.com/watch?v=UdbndwiYUy4 type: video:youtube source: "Matt Wolfe" published: 2026-06-05T14:17:07.191Z updated: 2026-06-05T14:17:22.835Z tags: ["ai", "machine-learning", "future"] reading_time: 1 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # I Didn’t Know AI Could Do THIS **[Matt Wolfe](https://daily.dev/sources/mreflow)** · 1 min read · 0 upvotes · 0 comments ## Summary Google's Gemini Omni model can generate video from visual inputs like maps and sketches. Demonstrated use cases include creating a first-person taxi cab driving video from a Google Maps screenshot with a drawn route, and generating drone POV footage from a hand-sketched camera path. The generated videos accurately follow the specified paths, including flying under bridges and past specific buildings. This opens up practical applications for filmmakers needing establishing shots without physical drone equipment. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Google's Gemini Omni can generate "anything from any input," including video](https://daily.dev/posts/google-s-gemini-omni-can-generate-anything-from-any-input-including-video-r2pzjzhqg) · XDA Developers · 3 upvotes · 0 comments - [Introducing Gemini Omni](https://daily.dev/posts/introducing-gemini-omni-fosehbhac) · DeepMind · 0 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#machine-learning](https://daily.dev/tags/machine-learning), [#future](https://daily.dev/tags/future) [View this post on daily.dev](https://daily.dev/posts/i-didn-t-know-ai-could-do-this-mipeyenrw)