Google has also unveiled a major update to its Flow service.
The company has released Nano Banana 2, a new visual generation model operating at Gemini Flash speed.
Introducing Nano Banana 2: Our best image generation and editing model yet. š
ā Google (@Google) February 26, 2026
Pro-level quality, at Flash speed. Rolling out today across @GeminiApp, Search, and our developer and creativity tools. pic.twitter.com/6oNWYhVSqp
This product leverages the Gemini knowledge base and real-time web search data. This approach enables the AI to more accurately render complex objects, generate infographics, and transform text notes into visual diagrams.
Nano Banana 2 can also generate clear and readable text within images, ranging from marketing layouts to greeting cards. Its built-in localization feature allows text to be tailored for any audience.
Generated by Nano Banana 2: an infographic of the water cycle. Source: Google.
The model produces detailed photorealistic images without sacrificing speed. Key differences between Nano Banana 2 and its predecessor include:
- Object consistency: The AI maintains the appearance of up to five characters and the accuracy of 14 objects within a single project.
- Execution accuracy: The system better understands complex text prompts and pays attention to subtle details, strictly adhering to user requests.
- Format flexibility: Full control over aspect ratios and resolutions from 512px to 4Kāsuitable for everything from vertical posts to widescreen displays.
- Visual quality: Bright lighting, rich textures, and sharp details while maintaining the speed characteristic of the Flash line.
4. Create assets with full control over aspect ratios and resolutions from 512px to 4K.
ā Google (@Google) February 26, 2026
From vertical social posts to 4K wide-screen backdrops, your visuals stay sharp, vibrant, and production-ready. pic.twitter.com/mKvw1AqozD
Nano Banana 2 will replace the Pro version in the Fast, Thinking, and Pro models of the Gemini app. Subscribers to Google AI Pro and Ultra will retain access to Nano Banana Pro.
The model is also integrated into Google Search (in AI and Lens modes) and is available in beta in AI Studio and the Gemini API.
Flow Update
Google has also introduced an updated version of its video generation service, Flow. Developers have completely redesigned the interface, merging image and video generation capabilities into a single workspace.
Today we're expanding Flow into a full AI creative studio. Weāve redesigned the experience and powerful new tools so you can draft, visualize, and refine your stories in a single, unbroken workflow.
ā Flow by Google (@FlowbyGoogle) February 25, 2026
Whatās new:
āØ An updated interface for seamless workflows
š¼ļø An easier way toā¦ pic.twitter.com/xrUkNaSMiU
The Flow service has integrated the best features from the experimental platforms Whisk and ImageFX. Nano Banana 2 has become part of the core functionality, allowing users to create images and immediately use them as frames for video generation without leaving the service.
The new asset grid simplifies searching, filtering, and sorting images and videos, as well as grouping them into collections. The Lasso tool allows precise selection of image areas for modifications via text promptsāsuch as "remove the person" or "add koi fish to the water." Direct drawing on images for indicating changes is also available.
According to the company, since its launch, Flow users have created over 1.5 billion images and videos for creative projects, including films, music videos, and advertising campaigns.
As a reminder, in February, Google introduced Gemini 3.1 Pro and updated its AI tool for vibe coding, Opal.