Google released Gemini Omni 1.2 Flash on November 5, extending native video generation to 15 seconds and reducing the price 30% from the previous version. The model is generally available through the Gemini API and Gemini for business at $0.07 per second for 720p video, according to a Google blog post.
Omni 1.2 Flash generates videos between 3 and 15 seconds in one-second increments, up from a 10-second maximum in Omni 1.1. The model supports multi-turn conversational editing, allowing users to refine specific details in a generated clip without re-generating the entire video. Google also offers draft generation at 360p or 720p with optional upscaling to 1080p or 4K.
Google says the model improved reference adherence when combining character images, product photos, style references, short motion clips up to three seconds, and audio cues. According to the company, faces, garments, packaging typography, and brand colors remain consistent across camera angles. The announcement cited virtual try-on sequences and product catalog rotations as use cases.
The model also claims stronger visual consistency across frames, with less drift or morphing during motion and camera transitions. Google described maintaining character, object, and scene details when interpolating between keyframes or extending clips to build longer sequences.