Google launches Nano Banana 2 Lite, it creates images in 4 seconds

Google has introduced Nano Banana 2 Lite, its fastest and most affordable AI image generation model yet. Alongside it, the company has expanded access to Gemini Omni Flash, giving developers quicker and more cost-effective tools to create AI-generated images and videos.

In Short

• Nano Banana 2 Lite promises to generate AI images in four seconds
• Google also expands Gemini Omni Flash for AI-powered video generation and editing
• Google says its new models are designed to help developers build faster, lower-cost AI workflows

The next time you type a prompt, your AI-generated image could be ready before you've even finished sipping your coffee. That's the promise behind Google's new Nano Banana 2 Lite image model, the latest and fastest addition to its Nano Banana image generation family. According to Google, Nano Banana 2 Lite is designed for developers who need to generate large volumes of AI images quickly without significantly increasing costs.

Google says Nano Banana 2 Lite is capable of generating AI images from text prompts in as little as four seconds, making it its fastest and most affordable Gemini image model to date. Alongside, The company has also made Gemini Omni Flash, its multimodal AI model for video generation and conversational editing more widely available.

Together, the two models aim to help developers build end-to-end AI workflows, from generating images to creating videos.

Nano Banana 2 Lite features

Nano Banana 2 Lite, listed as gemini-3.1-flash-lite-image, is built for high-speed creative workflows where latency and operating costs matter more than advanced reasoning. Google says the model is ideal for rapid prototyping, brainstorming visual ideas, generating large batches of images and other high-volume use cases. It is also the company's recommended replacement for the original Nano Banana model, gemini-2.5-flash-image.

One of the biggest highlights of Google’s new image model is speed. Google says Nano Banana 2 Lite can generate text-to-image outputs in around four seconds, allowing developers to iterate much faster during creative projects.

Nano Banana 2 Lite price

Google has also priced the model aggressively at $0.034 per 1K-resolution image, positioning it as the most cost-efficient option in the Nano Banana family for developers managing large-scale workloads or tighter budgets.

Despite prioritising speed, Google says the model delivers reliable prompt adherence, consistent characters across generated images and readable text within images, areas where AI image generators have traditionally struggled.

Google also clarified how Nano Banana 2 Lite fits into its broader AI image portfolio. While Nano Banana 2 Lite focuses on ultra-fast, high-volume image generation, Nano Banana 2 (Gemini 3.1 Flash Image) remains the company's all-round model, balancing image quality, speed and pricing for general-purpose use.

At the premium end sits Nano Banana Pro (Gemini 3 Pro Image), which is designed for professional workloads requiring greater reasoning, precision and creative control, even if image generation takes longer.

In short, Google has built the new Nano Banana Lite for speed, Nano Banana 2 for balance, and Pro for maximum quality and control.

Nano Banana 2 Lite availability

Google's Nano Banana 2 is now available through Google AI Studio, the Gemini API and the Gemini Enterprise Agent Platform. Google is also rolling it out across its consumer services, including AI Mode in Search, the Gemini app, NotebookLM, Google Photos, Google Flow, Stitch and Google Ads.

Gemini Omni Flash

Alongside Nano Banana 2 Lite, Google has also expanded access to Gemini Omni Flash, a multimodal model first unveiled at Google I/O. The model is now available to developers in public preview through Google AI Studio and the Gemini API, bringing high-quality video generation and conversational editing using text, images and video as inputs.

Google says Omni Flash is designed to let users refine videos using natural language prompts while maintaining consistency across multiple edits. It also supports multimodal referencing, allowing creators to combine text, images and videos to guide AI-generated results more accurately. The model is priced at $0.10 per second of generated video, matching the cost of Veo 3.1 Fast.

There are a few limitations for now. Omni Flash currently generates videos of up to 10 seconds, while support for longer videos is planned in a future update. Audio reference uploads, scene extension and reliable processing of short video references are also still under development.

Google says the two models are designed to work together. Developers can first generate images with Nano Banana 2 Lite and then pass those images to Gemini Omni Flash to animate them into short videos.

- Ends