Details
- Google AI Developers announced the launch of Nano Banana 2 Lite, described as its fastest, most cost-efficient Gemini Image model, optimized for high-throughput developer pipelines.
- Nano Banana 2 Lite is now available for developers to build high-velocity image pipelines, generating text-to-image outputs in about 4 seconds.
- The model is priced at $0.034 per 1,000 images, targeting rapid drafting and prototyping use cases where low per-image cost and speed are critical.
- Google also introduced Gemini Omni Flash, a video generation and editing model now available to developers in public preview.
- Gemini Omni Flash accepts text and image inputs to generate up to 10 seconds of 720p video with synchronized audio, supporting short-form content and quick iterations.
- The model additionally takes video inputs for conversational editing, allowing users to refine or modify existing footage through natural language interactions.
- Google highlighted a workflow demo using an interactive 3D globe, where users upload a photo to showcase Nano Banana 2 Lite’s rapid, context-aware image blending for personalized postcards.
- In the same demo, Omni Flash then extends the scene into video, illustrating how combining image and video models can produce richer, multimodal experiences.
- Both Nano Banana 2 Lite and Gemini Omni Flash are accessible to developers starting today through the links shared in the announcement.
- Google is positioning these models as building blocks for high-throughput creative and media pipelines, with clear emphasis on cost, latency, and integrated multimodal workflows.
Impact
By pairing a low-cost, high-speed image generator with a multimodal video model, Google strengthens its Gemini-based media stack for developers. This move pressures rivals like OpenAI and Anthropic to keep pace on pricing, latency, and integrated image–video tooling. For startups and enterprises, the new models can lower experimentation costs and accelerate deployment of automated creative workflows across ads, social content, and product experiences.
