Gemini Omni brings conversational editing to generated video
- Source
- x.com
- Date
By now, you've probably heard about Gemini Omni, our new model designed to create anything from any input, starting with video. But... what's the big deal? Let’s break it down 🧵👇
World understanding: Gemini Omni is built on Gemini's vast knowledge of history, science, and culture, so it can produce videos that are grounded in how the world actually works.
Reference anything: Gemini Omni extends Gemini's native multimodality, allowing you to blend combinations of text, audio, image, and video inputs into a high-quality, consistent video.
Conversational editing: Gemini Omni allows you to edit your videos using natural language (like Nano Banana, but for video). So you can easily change your characters, settings, and styles by just describing what you want.
Context
Gemini Omni makes generated video something users can revise through conversation. Google AI describes a model that accepts combinations of text, audio, images and video, then lets users request changes to characters, settings or visual style in ordinary language. References provide material for the video; follow-up instructions direct its revision. The useful capability in the May 19 thread is that continuing editing process, which the post compares to Nano Banana's editing but for video.
- postGoogle's week: EmbeddingGemma 2, Nano Banana 2.1, Gemini business agent
postGoogle opens SynthID watermark checks to everyone, with partner coverage
postGemma 4 orchestrates a plant DNA model to find crop mutations in minutes
articleGoogle's Project CC gives a family agent its own identity and sandbox
Checking sign-in…
Loading comments…