Gemini Omni 1.2 Flash goes generally available: 15-second clips at $0.07 per second for 720p
Synopsis
Gemini Omni 1.2 Flash is now generally available through the Gemini API and Gemini for business, extending native video generation from 10 seconds in Omni 1.1 to 15 seconds and allowing durations from 3 to 15 seconds in one-second increments. It adds multi-turn conversational editing, so a clip can be refined turn by turn, swapping a product or background or changing lighting and aspect ratio without regenerating the whole clip; 720p video costs $0.07 per second, 30% below Omni 1.1. In the official example, given the same static studio poster and five-layer animation prompt, 1.2 follows the reference image more closely than 1.1.
Interpretation
Gemini Omni 1.2 Flash lets users generate videos up to 15 seconds in a single pass and specify durations from 3 to 15 seconds in one-second increments, enough for complete stories, product explainers or a full social ad spot. The previous generation, Gemini Omni 1.1, capped native generation at 10 seconds. The official comparison uses the same static studio-lighting exhibition poster and the same five-layer animation prompt: Omni 1.1 Flash matches the reference image less closely than 1.2, while 1.2 builds the poster layer by layer on the dusty-pink cyclorama and hexagonal plinth, holding the ribbed glass, warm filament, faceted crystal and coiled-cord letterforms for HALO, GLOW and LUMEN through the final frame.
Editing happens in conversation on the same clip, turn by turn, swapping a product or background, changing lighting or weather, or switching aspect ratio, across full 15-second clips. Previously, producing variants meant re-briefing or regenerating the entire clip. The official example starts from one generated clip and swaps the background turn by turn from a striped pavilion tent to an oak forest, a stable with a white horse, a market fair and a stone castle, while keeping both characters' performances, armor reflections and camera framing intact.
Reference adherence is stronger: character, product and style images, motion clips up to three seconds and audio cues can be combined, with faces, garments, packaging typography and brand colors staying consistent across camera angles. Google states that Omni 1.2 Flash holds these details from start to finish, where earlier versions showed more visual drift or morphing across motion and camera transitions. The official example combines one model photo with front-and-back product shots of three outfits to generate a 15-second virtual try-on sequence across 360-degree turns and match cuts, keeping the model's identity and each garment's cut, drape and back details consistent.
Perspective
The report covers Google's release notes and official examples for Gemini Omni 1.2 Flash, aimed at developers, businesses and creators producing video at scale; Google says development continues to improve areas such as fast sports action, rapid script changes and complex physics.
Google lists fast sports action, rapid script changes and complex physics as areas still being improved, indicating these scenes are not yet ideal; the evidence for reference adherence and consistency comes from official example comparisons without quantitative metrics.