Exciting news for developers and creatives alike! We’re rolling out two powerful new AI models designed to supercharge your generative media workflows: Nano Banana 2 Lite and Gemini Omni Flash. These innovations promise to make experimentation faster, more affordable, and more capable than ever before.
The world of generative media thrives on iteration and creative freedom. With these cutting-edge models, you can seamlessly integrate rapid image generation with sophisticated video creation and editing, building truly immersive end-to-end multimedia experiences.
Introducing Nano Banana 2 Lite: Speed and Efficiency Unleashed
Meet Nano Banana 2 Lite (gemini-3.1-flash-lite-image), our latest image generation model engineered for sheer speed and cost-efficiency. It’s the ideal choice for developers who need to generate thousands of images quickly, perfect for rapid ideation and high-velocity pipelines.
This model is a significant upgrade and our recommended replacement for those currently using the original Nano Banana (gemini-2.5-flash-image). Switching over will instantly boost performance across critical dimensions, giving you immediate benefits without compromise.
Despite its focus on speed, Nano Banana 2 Lite doesn’t skimp on quality. You can expect reliable prompt adherence, impressive character consistency, and clear, legible in-image text rendering. For a deep dive into its full capabilities and integration details, be sure to check out the developer documentation.
Beyond developer platforms, Nano Banana 2 Lite is also making its way to various Google consumer surfaces. Look forward to experiencing its power in AI Mode in Search, the Gemini app, NotebookLM, Google Photos, Stitch, Google Flow, and Google Ads.
Gemini Omni Flash: The Future of Video Creation and Editing
Get ready for Gemini Omni Flash (gemini-omni-flash-preview), the groundbreaking model that merges Gemini’s multimodal reasoning with advanced video generation and editing. Now available to developers via the Gemini API and Google AI Studio, this model natively supports high-quality video creation and conversational editing.
You can input a combination of text, images, and existing video to bring your vision to life. This incredible power comes at a competitive price point of $0.10 per second of video output, matching the cost of Veo 3.1 Fast, making professional-grade video generation more accessible than ever.
Gemini Omni Flash is currently in public preview, offering an exciting glimpse into the future of video content. For comprehensive benchmarking information and detailed insights into its capabilities and regional limitations, consult the Google DeepMind’s Gemini Omni webpage and the developer documentation.
Chaining Models for Unprecedented Workflows
The true magic unfolds when you link these two powerful models together. Imagine using Nano Banana 2 Lite to quickly generate a stunning image, then seamlessly passing that image as a reference to Gemini Omni Flash to animate it into a high-quality video.
For multi-turn experiences, the Interactions API allows you to maintain session history and context, enabling users to stack up to three sequential edits. This creates incredibly fluid and dynamic creative workflows, pushing the boundaries of what’s possible.
To inspire your next project, we’ve created several demo apps that showcase the incredible synergy between Nano Banana 2 Lite and Gemini Omni Flash:
- Anywhere: Upload a selfie, and Nano Banana 2 Lite instantly transports you to iconic landmarks. Click an image, and Omni Flash animates it into a dynamic clip of your new location.
- Space Lift: Reimagine any room with this interior design app. Upload a photo, and Nano Banana 2 Lite generates stunning concepts. Once you find a design you love, tap to watch Omni bring it to life with a cinematic video showcase.
- Omni Product Studio: Convert static e-commerce images, often generated by Nano Banana 2 Lite, into compelling cinematic videos using Gemini Omni. This demo highlights how interactive media can emerge from multimodal inputs and quick image-to-video outputs.
Rest assured, both Gemini Omni and Nano Banana 2 Lite are built on Google’s secure infrastructure and incorporate SynthID watermarking. This crucial feature helps you verify AI-generated content through the Gemini app, Gemini in Chrome, or Search, promoting transparency and trust across the web.
Source: Google DeepMind Blog
