The Daily Tech TipSmarter Tech. A Brighter You. ⌨ Home
ai
ai

How do you use Gemini Omni 1.2 Flash to make and edit a 15-second video?

By Adam Neely · Nov 6, 2026
Quick answer: Google’s updated Gemini Omni 1.2 Flash video model now makes 15-second clips instead of 10, costs about 30 percent less, follows reference images more closely, and lets you refine the same clip over several conversational turns. Here is how to make a first clip, steer it with a photo, and edit it by chatting — in the Gemini app, AI Studio, or the Gemini API.

Google’s updated Gemini Omni 1.2 Flash video model now makes 15-second clips instead of 10, costs about 30 percent less, follows reference images more closely, and lets you refine the same clip over several conversational turns. Here is how to make a first clip, steer it with a photo, and edit it by chatting — in the Gemini app, AI Studio, or the Gemini API.

You have a scene in your head — a product, a pet, a tiny story — and you want it moving, not just described. Short answer: Gemini Omni 1.2 Flash is Google’s updated video model, and it now makes clips up to 15 seconds long, up from 10 seconds in the previous version. It costs about 30 percent less to run, follows a reference image more faithfully, and lets you keep improving the same clip over several back-and-forth messages instead of starting over each time.

You can use it in the Gemini app, in Google AI Studio, or through the Gemini API.Why it matters: Fifteen seconds is long enough for a complete little moment, where ten often cut the idea in half. Conversational editing matters just as much: most first drafts are almost right, and saying “keep everything, but slow the camera down” saves time and money.Make your first clip, step by step:1. Open the video tool: In the Gemini app or AI Studio, choose the video option and make sure Gemini Omni 1.2 Flash is the selected model.2.

Write one clear scene: Name the subject, the action, and the camera in a single prompt — for example, “a golden retriever puppy runs across a sunny kitchen toward the camera, low angle, bright morning light.” Vague prompts get vague videos.3. Steer it with a reference image: Upload a photo of your product, pet, or character and say what must stay the same — “keep this exact mug and logo, place it on a café table.” The updated model holds reference details better than the last one.4. Edit by conversation: Reply to the result with one change at a time — “make the light warmer,” “hold the last second longer,” “remove the person in the background.” Each reply revises the same clip.5.

Check the details before you share: Watch hands, faces, and on-screen words closely, and re-prompt just the faulty detail.Pro tip: Change one thing per message. Asking for five fixes at once makes it impossible to tell which instruction caused a new glitch.Ad’s take: The real upgrade is not the extra five seconds — it is being treated like a director who can say “again, but slower.”

Open on the homepage

Ask AI about this tip

Send this tip to your favorite AI assistant for a plain-language walkthrough, follow-up questions, or help applying it to your device.

Was this helpful?
Home