Google's Gemini Omni 1.2 Flash stretches AI video clips to 15 seconds and cuts pricing by 30 percent

Google Deepmind is making Gemini Omni 1.2 Flash generally available. The video-generation model now creates clips up to 15 seconds long, can be edited step by step via conversation, and costs just $0.07 per second at 720p, 30 percent less than its predecessor. Users who draft in low resolution and upscale only the final result can save even more. The article

The top 3

  1. Enhanced Workflow and Cost Efficiency: The model shifts video production toward an iterative, tiered workflow that reduces costs. Users can draft content at lower resolutions (360p/720p) and utilize conversational editing to refine specific details—such as background or lighting—before upscaling the final version to 1080p or 4K.
  2. Technical Improvements in Video Consistency: Gemini Omni 1.2 Flash utilizes improved reference adherence to maintain consistency in faces, clothing, and typography across camera angles. It achieves more fluid motion and clearer lip-sync, while reducing visual drift and unwanted jump cuts during complex camera movements like zooms or FPV flights.

Sources

Open the full topic