Nine questions about length, editing, price and the 1.1 switch.
What is Gemini Omni 1.2 Flash?
Google DeepMind’s video model, released November 5, 2026. It makes 3 to 15 second clips with sound from text, images and short motion clips, then edits them by conversation.
How long can Gemini Omni 1.2 Flash videos be?
From 3 to 15 seconds, set in one-second steps, with 10 as the default. On Creatide AI, 2× duration (beta) runs a single take to 30 seconds.
Can I edit a clip after it renders?
Yes. Follow-up messages swap products or backgrounds, change light or weather, switch between 16:9 and 9:16, extend the shot or fill between two frames, without starting over. On Creatide AI you make these edits by chat in Agent+.
What resolution does Gemini Omni 1.2 Flash support?
Drafts at 360p or 720p, upscales to 1080p or 4K, at 24 fps in 16:9 or 9:16. On Creatide AI every take exports up to 8K.
How many references can I add?
Up to 6 images for faces, products, outfits or style, plus motion clips of up to 3 seconds and audio cues.
How much does Gemini Omni 1.2 Flash cost?
The official Gemini API lists $0.023 a second at 360p, about $0.07 at 720p, $0.104 at 1080p and $0.209 at 4K. On Creatide AI it runs on plan credits, and paid plans include commercial rights.
What changed from Gemini Omni 1.1 Flash?
Clips grew from 10 to 15 seconds, the 720p price dropped about 30%, edits cover the full clip, and dialogue gained multi-speaker voice matching. Google routes 1.1 calls to 1.2 on December 3, 2026.
Is there a Gemini Omni Pro?
Not yet. As of November 2026 Google has released only the Flash tier of Gemini Omni for video.
Does Gemini Omni 1.2 Flash add a watermark?
Yes. Every clip carries Google’s invisible SynthID watermark, which marks it as AI-generated.