Skip to content
K = 0.731Subscribe
Original
ModelsGoogle AI · XFrom the source· @GoogleAI·· 1 hours agoSame news

24.1K views · 448 likes · 49 reposts (at collection)

Google Introduces Gemini Omni 1.2 Flash

Who
Google DeepMind
What
released Gemini Omni 1.2 Flash video generation model
When
Quote
We’ve made the model more cost-effective, bumped the video generation and editing limit up to 15 seconds, and made updates to how scenes hold together over time.

What happened

Google AI introduces Gemini Omni 1.2 Flash, saying the model is more cost-effective and raises the video generation and editing limit to 15 seconds. The update also addresses how scenes hold together over time, character speech, and visual glitches such as jump cuts.

The same story is shown in the picks as 《Google DeepMind Rolls Out Gemini Omni 1.2 Flash for Longer Video Generation》

Read next

See the full storyGoogle Rolls Out Gemini Omni 1.2 Flash for 15-Second Video

Reported by 3 sources

    Article

    Meet Gemini Omni 1.2 Flash ⚡️

    We’ve made the model more cost-effective, bumped the video generation and editing limit up to 15 seconds, and made updates to how scenes hold together over time. We've also given character speech an upgrade, reduced visual glitches like jump cuts, https://t.co/jjhjFmIs5p

    The story so far

    Google is rolling out Gemini Omni 1.2 Flash for video generation and editing through the Gemini API and Gemini for business, raising the clip limit to 15 seconds from 10 seconds in Omni 1.1. Google says 720p video costs $0.07 per second, 30% less than Omni 1.1. Google says the update improves reference adherence, conversational editing, speech and consistency, including how scenes hold together and visual glitches such as jump cuts. Logan Kilpatrick also cited cinematic camera POV controls and less visual drift. In Google Vids, users with a Google account or Google Workspace subscription can generate 15-second clips at no additional cost; video creation in the Gemini app is rolling out to Google AI Ultra subscribers.

    How the story developed · 2

    View full event
    1. 11/6 01:45 (UTC+8)

      Google Introduces Gemini Omni 1.2 Flash This report

    2. 11/6 01:07 (UTC+8)
      Google DeepMind Rolls Out Gemini Omni 1.2 Flash for Longer Video GenerationGoogle DeepMind
    Google / GeminiAI videoModel releases#Model release#Video#Google

    Keep up with AI, one email a day

    Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue · 2026-11-05