Google Launches Nano Banana 2 Image Model and Redesigned Flow Creative Studio

Google has launched Nano Banana 2, its latest visual generation model that combines Pro-level quality with the speed of the Gemini Flash lineup. Alongside the release, the company rolled out a comprehensive redesign of its Flow creative service.

«Introducing Nano Banana 2: Our best image generation and editing model yet. 🍌Pro-level quality, at Flash speed. Rolling out today across @GeminiApp, Search, and our developer and creativity tools.» — Google (@Google), original post

Nano Banana 2 Capabilities

The model leverages Gemini's knowledge base and real-time web search data. This approach enables the neural network to render complex objects more accurately, generate infographics, and transform text notes into visual diagrams.

A standout feature is the ability to generate clear, readable text directly within images — from marketing mockups to greeting cards. A built-in localization function automatically adapts text for any target audience.

Why It Matters

Nano Banana 2 delivers significant improvements over its predecessor across several dimensions:

• Object consistency: maintains the appearance of up to five characters and accuracy of 14 objects within a single project;
• Prompt accuracy: better comprehension of complex text prompts with attention to fine-grained details;
• Format flexibility: full control over aspect ratios and resolutions from 512px to 4K;
• Visual quality: vivid lighting, rich textures, and sharp detail without sacrificing Flash-tier speed.

«Create assets with full control over aspect ratios and resolutions from 512px to 4K. From vertical social posts to 4K wide-screen backdrops, your visuals stay sharp, vibrant, and production-ready.» — Google (@Google), original post

Availability

Nano Banana 2 will replace the Pro version across the Fast, Thinking, and Pro models within the Gemini app. Google AI Pro and Ultra subscribers will retain access to Nano Banana Pro. The model is also integrated into Google Search (AI mode and Lens), and available in preview through AI Studio and the Gemini API.

Flow Gets a Full Creative Studio Makeover

Google simultaneously overhauled its video generation service Flow, merging image and video creation capabilities into a unified workspace. The updated platform incorporates the best features from the experimental Whisk and ImageFX tools, with Nano Banana 2 serving as part of the core functionality.

«Today we're expanding Flow into a full AI creative studio. We've redesigned the experience and powerful new tools so you can draft, visualize, and refine your stories in a single, unbroken workflow.» — Flow by Google (@FlowbyGoogle), original post

Users can now create images and immediately use them as frames for video generation without leaving the platform. A new asset grid simplifies searching, filtering, and organizing content into collections. The Lasso tool allows precise selection of image areas for text-based edits — such as removing objects or adding elements to a scene.

According to Google, Flow users have created over 1.5 billion images and videos for creative projects since launch, including films, music videos, and advertising campaigns.

Earlier in February, Google introduced Gemini 3.1 Pro and updated its vibe-coding AI tool Opal.