Google Launches Gemini Omni Flash and Nano Banana 2 Lite
Gemini Omni Flash and Nano Banana 2 Lite bring faster image generation, video editing and scalable AI media tools to Google’s Gemini ecosystem.
AI creation is getting faster, cheaper and more flexible. Google has introduced two new generative media models, Gemini Omni Flash and Nano Banana 2 Lite, aimed at helping developers, creators and businesses move from idea to finished visual content with fewer steps.
The launch strengthens Google’s Gemini ecosystem by bringing together fast image generation, video creation and conversational editing in one broader workflow. Here's everything you need to know!
What Nano Banana 2 Lite brings to image creation
Nano Banana 2 Lite is Google’s fastest and most cost-efficient Gemini Image model in the Nano Banana family. It is built for high-volume workflows where speed, scale and cost control matter, such as rapid prototyping, product mock-ups, social media assets and visual drafting.
According to Google, the model can deliver text-to-image outputs in about 4 seconds and is priced at $0.034 per 1K-resolution image. This makes it especially useful for developers who need to generate many images quickly without increasing production costs too heavily.
The model is also positioned as the recommended replacement for the earlier Nano Banana model, known as Gemini 2.5 Flash Image. Google says Nano Banana 2 Lite offers improvements in speed, cost and quality, while retaining useful capabilities such as prompt adherence, character consistency and readable in-image text.
How Gemini Omni Flash supports video workflows
Gemini Omni Flash focuses on video generation and conversational editing. In simple terms, conversational editing means users can ask the model to change a video using natural language, rather than relying only on complex editing tools or manual timelines.
The model supports inputs such as text, images and video, making it suitable for creative workflows where references need to be carried across scenes. Google says it can help synchronise text, graphics and actions in a video, while also using Gemini’s broader knowledge to support more coherent visual storytelling.
Gemini Omni Flash is available to developers through Google AI Studio, the Gemini API and the Gemini Enterprise Agent Platform. It is priced at $0.10 per second of video output. However, Google notes some current limits, including 10-second video generations, no audio reference uploads in the Gemini API and some restrictions around video references and character consistency.
Why the two models matter together
The most practical use case is combining both models in a single pipeline. A user could first create an image with Nano Banana 2 Lite, then pass that image into Gemini Omni Flash to animate it into a video. This can support use cases such as e-commerce product videos, interior design previews, advertising concepts, location-based content and interactive creative tools.
Google has also highlighted demo apps that show these combined workflows, including tools for transforming selfies into landmark scenes, redesigning rooms and turning static product images into cinematic clips.
Google’s Veo 3.1 brings vertical video, higher-fidelity upscaling and better character consistency
The bottom line
Nano Banana 2 Lite is available through Google AI Studio, the Gemini API and Google’s enterprise platform, with rollout across consumer surfaces such as AI Mode in Search, the Gemini app, NotebookLM, Google Photos, Stitch, Flow and Google Ads. Gemini Omni Flash is also available in the Gemini app and Google Flow.
Google says both models use SynthID watermarking to support AI content transparency. For developers and businesses, the launch signals a clearer shift towards end-to-end generative media systems where images, videos and edits can be created through connected AI tools rather than separate production steps.