According to CoinMeta, Google's newly released video generation model Gemini Omni 1.2 can generate videos up to 15 seconds in length, which is a 50% increase from the previous version. The cost of generating 720p videos has been reduced by 30%, to just $0.07 per second, so generating a 15-second video now costs only $1.05. This version also performs better in maintaining consistency of characters and footage when continuously modifying videos. Users can chat to change the background of the same video to forests, stables, and castles, while retaining the original characters, actions, and camera angles. Additionally, the new version has improved lip-sync for multiple characters in conversations, as well as resolved the issue of sudden jumps in footage during continuous camera movements. In the preliminary rankings on November 5th, Omni 1.2 ranked first in both text-to-video and image-to-video generation, and third in video editing. The new model is now available to all users, and its 15-second video generation function is also being gradually made available to users of Flow, Google Vids, and Gemini App.