Google unveils Nano Banana 2 with faster image generation

Google has unveiled Nano Banana 2, the latest iteration of its widely used image generation model. Technically known as Gemini 3.1 Flash Image, it produces more lifelike visuals than the previous version. The model will now serve as the default image generator across the Gemini app's Fast, Thinking, and Pro modes.

Initially launched in August 2025, Nano Banana spurred millions of image creations within the Gemini app, particularly in markets such as India. The November release of Nano Banana Pro enabled users to produce images with greater detail and quality.

Nano Banana 2 preserves many of the high-fidelity traits of the Pro version while delivering faster image generation. According to Google, users can create images with resolutions from 512px up to 4K, supporting various aspect ratios.

Nano Banana 2 can maintain consistent character appearances across up to five characters and preserve fidelity for up to 14 objects within a single workflow, enhancing narrative coherence. Google notes that users can submit complex, nuanced requests for image generation. Additionally, the model produces media with more vibrant lighting, richer textures, and sharper details.

With this launch, Nano Banana 2 becomes the default image generation model across all Gemini app contexts. The company is also setting it as the default for image generation in its video editing tool, Flow.

In Google Search, Nano Banana 2 will power image generation results via Google Lens and AI Mode, rolling out across 141 countries on the Google app and on desktop and mobile web.

Subscribers to Google’s higher-tier plans, Google AI Pro and Ultra, can still access Nano Banana Pro for specialized tasks by regenerating images through the three-dot menu.

Save up to $300 or 30% on TechCrunch Founder Summit

1,000+ founders and investors gather at TechCrunch Founder Summit 2026 for a full day dedicated to growth, execution, and real-world scaling. Hear from founders and investors who have shaped the industry. Connect with peers facing similar growth challenges. Leave with actionable tactics you can use right away.

Offer ends March 13.

Save up to $300 or 30% on TechCrunch Founder Summit

1,000+ founders and investors gather at TechCrunch Founder Summit 2026 for a full day dedicated to growth, execution, and real-world scaling. Hear from founders and investors who have shaped the industry. Connect with peers facing similar growth challenges. Leave with actionable tactics you can use right away.

Offer ends March 13.

For developers, Nano Banana 2 will be available in preview via the Gemini API, Gemini CLI, and Vertex API. It will also be accessible through AI Studio and Antigravity, the company's development tool released last November.

Google stated that all images generated with the new model will carry a SynthID watermark, the company's identifier for AI-generated content. These images are also interoperable with C2PA Content Credentials, a standard developed by an industry consortium including Adobe, Microsoft, Google, OpenAI, and Meta. Google reports that since SynthID verification launched in the Gemini app in November, it has been used over 20 million times.