Google launches Nano Banana 2 Lite image model and Gemini Omni Flash video model
Google has released Nano Banana 2 Lite, a faster and more cost-efficient image generation model, and Gemini Omni Flash, a new model for video generation and editing. These models aim to streamline creative workflows for developers building generative media experiences. Nano Banana 2 Lite is available now for developers and rolling out to Google consumer products, while Gemini Omni Flash is in public preview for developers via API and AI Studio. This release allows for integrated image-to-video workflows and enhanced multimedia content creation.
- →Introduce Nano Banana 2 Lite for faster, cost-efficient image generation
- →Make Gemini Omni Flash available for video generation and editing
- →Enable integrated image and video generation workflows
- →Integrate new models into Google consumer products
- →Enhance safety and transparency with SynthID watermarking
Features (2) ›
- Introduce Nano Banana 2 Lite for faster, cost-efficient image generation
Nano Banana 2 Lite is Google's newest image model, designed for high throughput and speed. It offers text-to-image outputs in 4 seconds and costs $0.034 per 1K image, making it ideal for rapid ideation and high-volume developer pipelines. The model is recommended as a replacement for the legacy Nano Banana (gemini-2.5-flash-image).
- Make Gemini Omni Flash available for video generation and editing
Gemini Omni Flash is now available to developers via the Gemini API and Google AI Studio, offering high-quality video generation and conversational editing. The model supports text, image, and video inputs and is priced at $0.10 per second of video output. It enables features like natural language video refinement and multimodal referencing.
Maintenance (1) ›
- Integrate new models into Google consumer products
Nano Banana 2 Lite is rolling out to Google consumer surfaces including AI Mode in Search and the Gemini app. Gemini Omni Flash is also available in the Gemini app and Google Flow, enhancing user-facing generative media features.
Notes (2) ›
- Enable integrated image and video generation workflows
Developers can now combine Nano Banana 2 Lite for image generation with Gemini Omni Flash for video creation, enabling end-to-end multimedia experiences. Demo apps like 'Anywhere', 'Space Lift', and 'Omni product studio' showcase these integrated capabilities.
- Enhance safety and transparency with SynthID watermarking
Both Gemini Omni and Nano Banana 2 Lite utilize SynthID watermarking to verify AI-generated content. This feature can be accessed through the Gemini app, Gemini in Chrome, and Search, aiding users in understanding content origin.
https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-omni-flash-nano-banana-2-lite/