Google introduced artificial intelligence models for fast image and video processing
The company Google announced the release of two new artificial intelligence models: the Nano Banana 2 Lite image generator and the Gemini Omni Flash video tool. These developments will become available to developers in Google AI Studio and will be integrated into a wider range of the corporation’s services.
Nano Banana 2 Lite is the fastest and most affordable model in the Nano Banana lineup, capable of generating a large number of images in approximately four seconds each. The cost of use is $0.034 per image with a resolution of 1000 pixels. This model will also be featured in products such as AI Mode in Google Search, Gemini, NotebookLM, and Google Ads.
The development of Gemini Omni Flash provides the ability to create and edit videos using text and voice commands. Creation of multimodal videos based on text, images, and video fragments is supported. The generation cost is $0.10 per second of video. Currently, there is a limitation of creating clips up to ten seconds, but this functionality will expand in the future.
Google also offers to use both models together: create static images with Nano Banana 2 Lite and then pass them to Gemini Omni Flash for developing animated videos. This opens up new possibilities for creative projects and commercial use of artificial intelligence.
Google’s new developments are part of the company’s broader efforts to enhance AI technologies. This is an important step towards improving tools for developers and creating innovative solutions for end users.
| Model | Purpose | Generation Speed | Cost |
|---|---|---|---|
| Nano Banana 2 Lite | Image Generation | 4 seconds per image | $0.034 per image |
| Gemini Omni Flash | Video Creation | 10 seconds of video | $0.10 per second |
