Google has launched Nano Banana 2 Lite, the latest addition to its in-house AI image generation lineup. In a blog post on Tuesday, the company said that Nano Banana 2 Lite and Gemini Omni Flash are now available as tools for high-volume, fast-turnaround workflows.
Nano Banana 2 Lite generates images in approximately four seconds and costs $0.034 per 1,000 images. This makes it the fastest and cheapest image model in the Nano Banana family. Google is positioning it as a direct replacement for the original Nano Banana, which has now been designated a legacy model. It sits below Nano Banana 2, which Google describes as the "generalist workhorse" of the lineup, and below Nano Banana Pro for more demanding use cases. All generated content is automatically tagged with Google's SynthID digital watermark.

The model is available through Google AI Studio, the Gemini API, and the Gemini Enterprise Agent Platform for developers. On the consumer side, it is accessible through the Gemini app, AI Mode in Google Search, NotebookLM, Google Photos, Stitch, Google Flow, and Google Ads. On Arena's text-to-image leaderboard, Nano Banana 2 Lite currently sits at fifth, behind OpenAI's gpt-image-2, which leads the pack, and Microsoft's MAI-Image-2.5 in fourth.
Alongside the new Nano Banana 2 Lite, Gemini Omni Flash is now available in public preview through Google AI Studio, the Gemini API, and the Gemini app. It supports video generation and editing using text, image, and video inputs, with natural language editing, multimodal references, and text synchronized with on-screen actions. Videos are currently capped at 10 seconds, with longer durations coming later. The model is priced at $0.10 per second of video output, matching Veo 3.1 Fast.

Frequently Asked Questions
TweakBot answers common questions about this news using TweakTown's own coverage from this page and related content from our archive. Tap a question to reveal the answer, or type your own below.
What are the practical limits on image resolution or dimensions when generating images with Nano Banana 2 Lite via the Gemini API or AI Studio?
How does the SynthID watermarking affect downstream use in advertising or commercial distribution for images produced by Nano Banana 2 Lite?
What input file formats and codecs are supported when using Gemini Omni Flash for video generation and editing through Google AI Studio or the API?
Are there any documented latency or throughput differences when running Nano Banana 2 Lite vs Nano Banana 2 or Nano Banana Pro for high-volume batch image generation?
Have a question not listed here? Ask below and TweakBot will answer it.
Google also demonstrated how the two models work together, with Nano Banana 2 Lite generating a still image that Gemini Omni Flash then animates into a short video. The company is pitching this workflow to advertisers and e-commerce teams through a new demo app called Omni Product Studio.




