3 minute readnew delhiUpdated: July 1, 2026 12:01 PM IST
Google has introduced Nano Banana 2 Lite, its latest AI image generation model focused on speed and cost efficiency, alongside the wide availability of Gemini Omni Flash, its multimodal AI video generation and editing model.
According to the company, Nano Banana 2 Lite is currently available through Google AI Studio, Gemini API, and Gemini Enterprise Agent Platform. It has also been rolled out to consumer products such as AI Mode in Search, the Gemini app, NotebookLM, Google Photos, Stitch, Google Flow, and Google Ads.
Nano Banana 2 Lite is designed for rapid imaging workflows and large-scale deployments where latency and operational costs are key considerations. Google says the model can generate text-to-image output in about 4 seconds and costs $0.034 per 1000-resolution image.
Google is positioning this model as a replacement for its previous Nano Banana product, saying it delivers improved image quality, lower costs, and faster processing speeds while maintaining rapid accuracy, character consistency, and text rendering capabilities.
In addition to image models, the company has also expanded access to Gemini Omni Flash for developers. This model was first introduced during Google I/O 2026 and is now available through Google AI Studio, Gemini API, and Gemini Enterprise Agent Platform.
Gemini Omni Flash supports video generation and editing using a combination of text, image, and video inputs. Google says this model enables conversational editing with natural language prompts, multimodal references, and synchronization between text, graphics, and video actions. The price is $0.10 per second of video output, the same as Veo 3.1 Fast, a speed-optimized AI video generation model powered by Google DeepMind.
However, the current version is limited to 10-second video generation, and features such as audio references, scene expansion, and full support for longer video references are in development, the company said.
Story continues below this ad
Google said the two models can be combined within a single workflow, so developers can use Nano Banana 2 Lite to generate images and animate them with Gemini Omni Flash. The company also released a demo application that showcases use cases such as virtual travel experiences, interior design visualization, and e-commerce video creation.
Additionally, Google said both models incorporate SynthID watermarking technology as part of its efforts to improve transparency and verification of AI-generated content.
(This article was curated by Shivani P Menon, intern at The Indian Express)
