OFICIAL Google DeepMind Blog

Start building with Nano Banana 2 Lite and Gemini Omni Flash

What happened
Based on Google DeepMind Blog · Jun 30, 2026

Google introduced Nano Banana 2 Lite, a faster and more cost-efficient image generation model, and Gemini Omni Flash for high-quality video generation and editing. Both models are now available to developers and consumers, enabling rapid multimedia workflows and creative iterations.

🚩 Report a correction ↗ Open source
Start building with Nano Banana 2 Lite and Gemini Omni Flash
Google DeepMind Blog — Google DeepMind Blog
Key points
·
Google is making it easier to experiment and scale your ideas with Nano Banana 2 Lite, its fastest, most cost-efficient Gemini Image model, and Gemini Omni Flash for high-quality video generation and conversational editing.
·
Today, the company is making it faster and easier to experiment, refine and scale your ideas with two major releases: Building with generative media is often about creative iteration.
·
With these two models, developers can build comprehensive, end-to-end multimedia experiences that connect rapid image generation with video creation and editing.
·
Whether your workflow requires generating thousands of images or editing multi-turn video sequences, you now have two new models to build faster, iterate seamlessly and bring your creative vision to life.
Key numbers
·
Priced at $0.
·
10 per second of video output, it matches the cost of Veo 3.

Google has launched Nano Banana 2 Lite, a new version of its Gemini Image model designed for rapid image generation with a focus on speed and cost efficiency. The model is positioned as a replacement for the first Nano Banana release, offering improved performance across key metrics such as latency and cost per 1,000 images. Developers can integrate it into existing pipelines to accelerate creative workflows without compromising prompt adherence or text rendering quality.

Nano Banana 2 Lite is now accessible on Google’s consumer platforms, including AI Mode in Search, the Gemini app, NotebookLM, Google Photos, Stitch, Google Flow, and Google Ads. The model supports developers in generating thousands of images quickly, making it suitable for high-velocity projects where iteration speed is critical. Documentation and integration guides are available for developers to begin using the model immediately.

Gemini Omni Flash, introduced alongside Nano Banana 2 Lite, enables high-quality video generation and conversational editing from text, image, or video inputs. Priced at $0.10 per second of video output, it matches the cost of Veo 3.1 Fast. The model is available in public preview through the Gemini API and Google AI Studio, with regional limitations and detailed benchmarks accessible via Google DeepMind’s documentation.

Google also provided demo applications to illustrate practical use cases for both models. Anywhere transforms selfies into animated landmark clips, Space Lift reimagines interior spaces with cinematic showcases, and Omni Product Studio converts static images into e-commerce videos. Both models use SynthID watermarking for content verification, accessible through the Gemini app, Chrome, or Search.

Original source → Deals on Clipraptor.com →