Nano Banana 2 Brings Pro Image Quality to Gemini Flash Speed

Google DeepMind

Feb 26, 2026 · Updated Apr 25, 2026

Nano Banana 2 brings Pro-tier image capabilities to Gemini Flash speed — subject consistency, world-knowledge grounding, and 4K output. It's now the default in Gemini app, Search, AI Studio, Google Ads, and Flow, removing the quality trade-off from fast iteration.

Nano Banana 2 (Gemini 3.1 Flash Image) combines Nano Banana Pro's intelligence with Flash inference speed. It maintains consistency across five characters and 14 objects in a workflow — keeping storyboards and ad campaigns coherent. World knowledge grounding uses real-time search data for accurate infographics, diagrams, and localized signage. Precision text rendering handles marketing mockups and multilingual image translations. Output covers 512px to 4K.

Previously teams had to choose between fast-but-rough or slow-but-polished generation. Nano Banana 2 closes that gap, rolling out as the default across Gemini app, Google Search, AI Studio, Google Ads, Flow, and Google Cloud.

Developers can access gemini-3.1-flash-image-preview in AI Studio and the Gemini API at Flash-tier pricing. Pro and Ultra subscribers retain Nano Banana Pro access via the three-dot regenerate menu for high-fidelity tasks.

View the full update on blog.google

Google DeepMind

@GoogleDeepMindFeb 26

We’re launching Nano Banana 2, built on the latest Gemini Flash model. 🍌 It’s state-of-the-art for creating and editing images, combining Pro-level capabilities with lightning-fast speed. 🧵

491

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

See all AI news & updates from Google →

Keep reading

Google Moves Nano Banana Image Models to GA with 4K Support

Google moved its Nano Banana image generation models, including Nano Banana 2 and Nano Banana Pro, to General Availability via the Gemini API. This transition from preview to production-ready status enables developers to integrate high-fidelity 4K visuals and real-time search grounding into stable applications.

Google AI StudioMay 6

Google AI Studio Integrates Nano Banana to Automate App Asset Generation

Google AI Studio integrated the Nano Banana image model to automatically generate custom icons and assets during the application build process. A redesigned edit tool also introduces visual controls for selecting UI components and annotating designs directly on the interface. This shift moves AI-assisted development from text-only prompting to a hybrid visual workflow for faster prototyping.

Google Gemini Integrates Personal Intelligence to Generate Images From Your Interests

GeminiMay 12

Google Gemini Integrates Personal Intelligence to Generate Images From Your Interests

Google integrated its Personal Intelligence context layer with the Nano Banana 2 image model to enable personalized image generation in the Gemini app. By using user interests and Google Photos data, the system creates imagery that reflects a user's specific lifestyle and tastes without requiring detailed manual prompting.

Google DeepMindMay 20

Google Flow Adds Agentic Editing and Character Consistency via Gemini Omni

Google updated its Flow creative studios with Gemini Omni Flash to enable precise video editing and stable character identities across scenes. By introducing an autonomous agent for batch editing and natural language tool creation, Google is shifting AI video from single-clip generation to a managed production workflow.