By Ken Muthomi - Reporter
USA ,June 1 ,2026 - Google has launched Nano Banana 2 Lite and Gemini Omni Flash, two AI models that are aimed at making it faster for developers and users to create and scale AI-generated Videos and images.
According to the tech giant, the two tools will be available in Google AI Studio, the Gemini API, and the Gemini Enterprise Agent Platform.
Google has said that the models will enable content developers to build comprehensive, end-to-end multimedia experiences that connect rapid image generation with video creation and editing.
Nano Banana 2 Lite
This is a model that Google has described as the fastest, most cost-efficient image model in its catalogue, and it is specifically designed for rapid ideation and high-velocity developer pipelines.
The model delivers text-to-image output in 4 seconds, making it ideal for interactive prototyping and rapid visual drafting. The model will be cost-effective, especially for developers focused on drafting, ideating, managing operational budgets, or low-bandwidth usage.
Google has recommended it as a replacement for developers currently using our first version of Nano Banana (gemini-2.5-flash-image).
Apart from developer platforms, the model shall also be embedded in Google consumer surfaces including AI Mode in Search, Gemini app, NotebookLM, Google Photos, Stitch, Google Flow, and Google Ads.
“Despite prioritizing speed, Nano Banana 2 Lite retains reliable prompt adherence, strong character consistency, and legible in-image text rendering,” the company assured.
Gemini Omni Flash
More from Kenya
Google has said that the model is being rolled out to developers through the Gemini API and Google AI Studio, natively supporting high-quality video generation and conversational editing from a combination of text, image, and video inputs. This model is priced at $0.10 per second of video output.
The model is especially ideal for conversational video editing, multimodal referencing, Real- World knowledge, as well as Text and action synchronization.
However, the model has some limitations, including offering 10-second video generations, and uploading audio references and scene extension is not yet supported in the Gemini API for this model.
It also does not correctly process video references up to 3 seconds in duration, as well as some limitations in Character consistency when changing scenes or panning movements.
Users can chain these models together by using Nano Banana 2 Lite as an image generation model, then pass that image as a reference to Gemini Omni Flash to animate it into a video.
“Plus, by using the Interactions API for these multi-turn experiences, you can maintain session history and context so users can stack up to three sequential edits,” Google stated.
Discover more Kenya updates