Google has launched Nano Banana 2 Lite, the latest product in its in-house AI image generation lineup. in blog post On Tuesday, the company announced 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 about 4 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 this as a direct replacement for the original Nano Banana, which is currently designated as a legacy model. It sits below the Nano Banana 2, which Google describes as the “generalist flagship” of the lineup, and the Nano Banana Pro for more demanding use cases. All generated content is automatically tagged with Google’s SynthID watermark.
View gallery – 3 images
This model is available through Google AI Studio, Gemini API, and Gemini Enterprise Agent Platform for developers. On the consumer side, it can be accessed 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 ranks at number five. OpenAI gpt-image-2 is at the top, followed by Microsoft’s MAI-Image-2.5 in fourth place.
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. Supports video generation and editing using text, image, and video inputs, with natural language editing, multimodal referencing, and text synchronized with on-screen actions. Currently, the video limit is 10 seconds, but longer lengths will be released in the future. This model costs $0.10 per second of video output, comparable to the Veo 3.1 Fast.
FAQ
TweakBot answers frequently asked questions about this news using TweakTown’s own reporting from this page and related content from our archives. Tap a question to see the answer, or enter your answer below.
Question 01
When generating images with Nano Banana 2 Lite via Gemini API or AI Studio, what are the actual limitations on image resolution or size?
Question 02
How does the SynthID watermark affect the downstream use of images created by Nano Banana 2 Lite in advertising or commercial distribution?
Question 03
What input file formats and codecs are supported when using Gemini Omni Flash for video generation and editing via Google AI Studio or API?
Question 04
Is there any documented delay or throughput difference when running Nano Banana 2 Lite and Nano Banana 2 or Nano Banana Pro to generate large batch images?
Google also demonstrated how the two models work together, with the Nano Banana 2 Lite generating a still image that Gemini Omni Flash animated 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.
