- Google launched Nano Banana 2 Lite, its fastest and most affordable AI image generation model.
- Gemini Omni Flash is now available to developers for AI-powered video creation and editing.
- Both models are available through Google AI Studio, the Gemini API, and the Gemini Enterprise Agent Platform.
Google has launched Nano Banana 2 Lite, a new AI model for creating images, and expanded access to Gemini Omni Flash, its AI model for creating and editing videos. The company said the new models will help developers build AI apps faster and at a lower cost.
According to Google, both models are now available in Google AI Studio, the Gemini API, and the Gemini Enterprise Agent Platform. Google is also bringing Nano Banana 2 Lite to products such as AI Mode in Search, the Gemini app, NotebookLM, Google Photos, Google Flow, Stitch, and Google Ads. Gemini Omni Flash is also available in the Gemini app and Google Flow.
Nano Banana 2 Lite is built for speed
Google said Nano Banana 2 Lite, officially named Gemini 3.1 Flash Lite Image, is the fastest and most affordable image model in the Nano Banana family. The company said it is the recommended upgrade for developers using the older Nano Banana model based on the Gemini 2.5 Flash Image.
According to Google, Nano Banana 2 Lite can generate images from text prompts in about four seconds. The model costs $0.034 per 1,000 generated images, making it a low-cost option for developers who need to create large numbers of images.
Google said the model follows text prompts accurately, keeps characters consistent across different images, and produces clear text within images. The company said these features make it useful for quickly creating ideas, testing designs, and building image-based applications.
Google offers models for different needs
Google said each Nano Banana model is designed for a different purpose. Nano Banana 2 Lite is made for creating images quickly and in large numbers. Nano Banana 2 offers a good balance between speed and image quality. Nano Banana Pro is designed for more advanced work that needs higher accuracy and better control.
Gemini Omni Flash adds AI video tools
Google also announced that Gemini Omni Flash is now available to developers in public preview. The model can create and edit videos using text, images, and short video clips.
According to Google, Gemini Omni Flash costs $0.10 per second of generated video, the same price as Veo 3.1 Fast.
Google said developers can edit videos by giving simple text instructions. The model can also use text, images, and videos together to create more consistent results. In addition, Gemini Omni Flash uses Gemini’s built-in knowledge to help create videos with better details and more natural storytelling.
Some features are still limited
Google said Gemini Omni Flash is available in public preview and still has some limitations.
Right now, the model can generate videos that are up to 10 seconds long. Support for longer videos will be added later. Audio reference uploads and scene extension are not yet available through the Gemini API. Google also said video references longer than three seconds are not fully supported, and character consistency during scene changes or camera movement is still being improved.
How the models work together
Google said developers can use Nano Banana 2 Lite and Gemini Omni Flash together to create complete image-to-video projects. For example, users can first generate an image with Nano Banana 2 Lite and then use Gemini Omni Flash to turn that image into a short animated video.
Google also shared several demo apps to show how the two models work together. Anywhere lets users upload a photo or take a selfie, places them in famous locations, and turns the image into a short video. Space Lift lets users upload a photo of a room, creates different design ideas, and then makes a video of the new look. Omni Product Studio turns product images into short promotional videos that businesses can use for online shopping.
AI safety features
Google said both Nano Banana 2 Lite and Gemini Omni Flash include SynthID watermarking, which helps identify AI-generated content. The company said users can check AI-generated images and videos through the Gemini app, Gemini in Chrome, and Google Search.
Keep up with the tech that actually matters.
Add us as a preferred source on Google Search for quicker access to our coverage.
