Google DeepMind has announced the general availability of Gemini Omni 1.2 Flash, a video-generation model that now allows users to create video clips up to 15 seconds long. This update not only enhances the functionality of the model but also offers a significant pricing reduction, with costs dropping by 30 percent to just $0.07 per second at 720p resolution.
The new capabilities include step-by-step editing through conversational prompts, making it easier for users to craft their desired video content. Additionally, users can draft in lower resolutions and upscale only the final output, providing further cost savings and efficiency in the video production process.
This launch positions Google at the forefront of the rapidly evolving AI video generation market, where user-friendly features and affordability are becoming increasingly important.
Compiled automatically by the Tech AI Newsdesk from public AI-news sources and summarised in our own words.
Frequently asked questions
What is Gemini Omni 1.2 Flash?
Gemini Omni 1.2 Flash is a video-generation model announced by Google DeepMind that allows users to create video clips up to 15 seconds long.
How has the pricing changed for Gemini Omni 1.2 Flash?
The pricing has been reduced by 30 percent, now costing just $0.07 per second at 720p resolution.
What new features does Gemini Omni 1.2 Flash offer?
It includes step-by-step editing through conversational prompts and the ability to draft in lower resolutions before upscaling the final output.
