开始使用 Nano Banana 2 Lite 和 Gemini Omni Flash 进行构建

Jun 30, 2026 We’re making it easier to experiment and scale your ideas with Nano Banana 2 Lite, our fastest, most cost-efficient Gemini Image model, and Gemini Omni Flash for high-quality video generation and conversational editing. Today, we’re making it faster and easier to experiment, refine and scale your ideas with two major releases: Building with generative media is often about creative iteration. With these two models, developers can build comprehensive, end-to-end multimedia experiences that connect rapid image generation with video creation and editing. Whether your workflow requires generating thousands of images or editing multi-turn video sequences, you now have two new models to build faster, iterate seamlessly and bring your creative vision to life. Watch a side-by-side comparison of image generation speed and quality between Nano Banana 2 Lite and Nano Banana 2 using a simple prompt. Nano Banana 2 Lite (gemini-3.1-flash-lite-image) is designed for rapid ideation and high-velocity developer pipelines where speed and cost are the primary constraints. It’s our recommended replacement for developers currently using our first version of Nano Banana (gemini-2.5-flash-image), you can swap it out now for immediate benefits across key performance dimensions. Performance benchmarks for Nano Banana 2 and 2 Lite compared to competitor AI image models, evaluating trade-offs between generation/editing quality (Elo scores), processing latency and cost per 1K-resolution image. Despite prioritizing speed, Nano Banana 2 Lite retains reliable prompt adherence, strong character consistency and legible in-image text rendering. To see the full list of model capabilities and how to integrate check out the developer docs. Alongside its release on developer platforms, Nano Banana 2 Lite is also coming to Google consumer surfaces including AI Mode in Search, Gemini app, NotebookLM, Google Photos, Stitch, Google Flow, and Google Ads. Watch as someone uses Gemini Omni to perform four digital magic tricks, like pulling a 3D balloon word out of her phone and pouring water from the screen into a glass. There is a small “original" video in the corner revealing how she actually filmed the tricks before the Omni generated special effects were added. At Google I/O we introduced Gemini Omni Flash, the model where Gemini’s multimodal reasoning meets video generation and editing. Today, Gemini Omni Flash (gemini-omni-flash-preview) is rolling to developers via 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 competitively at $0.10 per second of video output, which is the same as Veo 3.1 Fast. Omni Flash shines in: For comprehensive benchmarking information, please visit Google DeepMind's Gemini Omni webpage. Limitations: Gemini Omni is available in public preview starting today in Google AI Studio and the Gemini API. To see the full list of model capabilities and regional specific limitations check out the developer docs. The real magic happens when you chain these models together. Use Nano Banana 2 Lite as a high-speed image generation model, then pass that image as a reference to Gemini Omni Flash to animate it into a high-quality 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. To help you get started we created a few demo apps you can remix that let you experience how you can pair both Nano Banana 2 Lite and Gemini Omni Flash into one workflow. Anywhere is a demo app built to showcase the strong capabilities of both models. Take a selfie or upload a photo, and the app uses Nano Banana 2 Lite to instantly transport you to dozens of iconic landmarks. Then, when an image is clicked, Omni Flash is used to turn the generated image into an animated clip of the location. Space Lift is a demo interior design app powered by Nano Banana 2 Lite and Gemini Omni, that lets you instantly reimagine any room by uploading a photo. The app automatically generates fully realized concepts across various design aesthetics. Once you find a look you love, tap the video button to watch Omni bring the design to life with a cinematic showcase, letting you experience your new space in motion before making it a reality. Omni product studio is a demo app that converts static images created by Nano Banana 2 Lite into cinematic e-commerce videos created by Gemini Omni. This demo illustrates building interactive media by merging multimodal inputs through quick interaction with an image-to-video output. Built on Google’s secure infrastructure, Gemini Omni and Nano Banana 2 Lite use SynthID watermarking. You can verify AI content through the Gemini app, Gemini in Chrome or Search. Learn more about how we're expanding our verification tools to help you understand how content was created and edited across the web. Nano Banana 2 Lite resources: Gemini Omni Flash resources: