The Pulse
Google Rolls Out Gemini Omni 1.2 Flash With Native 15-Second Video Generation
Google says Gemini Omni 1.2 Flash offers native video generation and editing for clips up to 15 seconds. Google says it cut the price by 30% from Gemini Omni 1.1 and added multi-turn editing and stronger reference following.
AI.info Team · Written with AI · fact-checked ·
Google said on Nov. 5 that it is rolling out Gemini Omni 1.2 Flash, bringing native video generation and editing for clips up to 15 seconds. The model adds multi-turn conversational editing and improved reference following, according to Google. Google says the price is 30% lower than Gemini Omni 1.1, at $0.07 per second for 720p video.
Google says clips can run up to 15 seconds
Google says Gemini Omni 1.2 Flash generates and edits video natively for up to 15 seconds, compared with 10 seconds for Omni 1.1. Users can set a duration in one-second increments from three to 15 seconds. Google says creators can draft at 360p or 720p, make a follow-up edit, and upscale selected work to 1080p or 4K. The company says those steps keep costs down.
Google says references guide characters, products and style
Google says users can combine images of characters, products or visual styles with motion clips of up to three seconds and audio cues. Google says the model holds onto those details from start to finish. Google says faces, garments, packaging typography and brand colors stay consistent across camera angles. One Google example uses a model photo and front-and-back product shots of three outfits to generate a 15-second virtual try-on sequence with 360-degree turns and match cuts.
Google also says the update improves consistency from a clip's first frame to its last. Google says products, characters, props and environments stay consistent across motion and camera transitions, with less visual drift or morphing. Google says this holds when interpolating between a first and last keyframe or extending a clip into a longer sequence.
Google says follow-up prompts edit the same clip
Google says multi-turn conversational editing lets users refine an existing clip instead of generating it again from scratch. Google lists changing a product or background, adjusting lighting or weather, and switching aspect ratio as examples. The feature works across full 15-second clips, the company says, and can produce ad variants without re-briefing or re-generating.
Google also describes more fluid dialogue, clearer lip-sync and distinct multi-speaker conditioning. The company says those capabilities apply to multi-character dialogue in Flow, explainers in Gemini for business, and videos made in Google Vids with avatars, music and narration. For camera direction, Google says users can direct continuous movements, including flythroughs, zoom-outs and orbits, with significantly fewer unwanted jump cuts.
Google says the model is rolling out across its products
Google says Gemini Omni 1.2 Flash is generally available through the Gemini API and Gemini for business, backed by Google Cloud's enterprise-grade infrastructure and security. Google says Provisioned Throughput is available and outputs carry an imperceptible SynthID watermark. Developers can prototype in Google AI Studio and use the Gemini API; businesses can try the model in the Google Cloud console.
Google says Google Vids offers 15-second clips at no additional cost with a Google account or Google Workspace subscription. It says the Gemini app is rolling out 15-second video creation to Google AI Ultra subscribers, while Flow supports scene direction and multi-turn edits. Google says development is ongoing to improve fast sports action, rapid script changes and complex physics.