- Published on
Google Launches Gemini Omni 1.1 Flash Video Generation AI Model with Up to 4K Resolution
- Authors
- Name
- DeepHorus
Google officially released its latest video generation artificial intelligence model, Gemini Omni 1.1 Flash, on August 27 local time. The core highlight of this new model is its ability to generate ultra-high-definition videos with resolutions up to 4K, marking an important step by Google in the field of AI video creation.
The released Gemini Omni 1.1 Flash brings several key upgrades in functionality. One of these is the scene extension feature, which allows users to seamlessly continue existing videos, adding up to 10 seconds each time, with a single video extendable to a maximum of 40 seconds. Additionally, users can specify the first and last frames of a video, enabling the AI to automatically generate smooth transitional content in between.
In terms of performance and cost, the new model offers more flexible options. Compared to the standard 720p resolution of the previous Omni 1.1, the new 360p preview mode can increase generation speed by up to 60% and reduce costs to one-third of the original, making it ideal for rapid creative iteration. For final productions, the model supports direct output of high-resolution videos at 1080p and 4K.
A notable feature is video reference. When constructing scenes, users can introduce a reference video clip of up to 3 seconds, which the AI will use to maintain consistency in the background and characters, thereby enhancing the coherence of the generated content.
In terms of pricing, Gemini Omni 1.1 Flash adopts a per-second billing model. Generating 360p video costs $0.03 per second (approximately 0.2 RMB), 720p video costs $0.1 per second (approximately 0.67 RMB). For higher-definition 1080p video, the price is $0.15 per second (approximately 1 RMB), while the highest quality 4K video is priced at $0.3 per second (approximately 2 RMB).
The launch of this new model is expected to provide more powerful AI-assisted tools for content creators, film studios, and the advertising industry, especially in areas such as storyboard creation, prototype validation, and final production. By reducing generation costs and increasing speeds at specific resolutions, Google aims to attract a broader range of users for creative exploration.
Industry analysts believe that as competition in generative AI technology intensifies in the video domain, Google's upgrade not only improves output quality but also consolidates its market position through differentiated feature settings and pricing strategies. In the future, the depth and breadth of AI video generation tools in creative industries are expected to further expand.
