Google has introduced Nano Banana 2, its latest state-of-the-art image generation model, marking a major upgrade to its Gemini-powered creative tools.
The new model, formally known as Gemini 3.1 Flash Image, combines the high-speed performance of Gemini Flash with the advanced intelligence and visual quality previously reserved for Nano Banana Pro. The result, Google says, is a faster, more accessible tool capable of delivering studio-quality visuals with improved reasoning and precision.
Intelligence and visual quality at Flash speed
Nano Banana 2 integrates Gemini’s real-world knowledge base and real-time web search capabilities to render more accurate and context-aware images. This expanded intelligence allows users to generate not only photorealistic visuals but also infographics, diagrams and data visualizations grounded in current information.
The model also significantly improves text rendering within images. Users can create accurate, legible text for marketing materials, greeting cards and promotional assets. In addition, Nano Banana 2 supports in-image translation and localization, enabling content to be adapted for global audiences without leaving the creative workflow.
Enhanced creative control
Google says Nano Banana 2 closes the gap between speed and visual fidelity, offering high-resolution outputs while maintaining rapid generation times.
Key upgrades include:
- Subject consistency: The model can maintain character resemblance for up to five characters and preserve the fidelity of up to 14 objects within a single workflow. This enables users to storyboard narratives without visual inconsistencies.
- Improved instruction following: Enhanced adherence to complex prompts ensures the final image more accurately reflects user intent.
- Production-ready specifications: Users can generate assets in multiple aspect ratios and resolutions, ranging from 512 pixels to full 4K. This flexibility supports everything from vertical social media posts to widescreen displays.
- Visual fidelity upgrade: Nano Banana 2 delivers richer textures, sharper details and more vibrant lighting while retaining the rapid response times associated with Gemini Flash.
Broad rollout across Google products
Nano Banana 2 is rolling out across Google’s ecosystem starting today.
In the Gemini app, the model will replace Nano Banana Pro across the Fast, Thinking and Pro modes. However, Google AI Pro and Ultra subscribers will still be able to access Nano Banana Pro for specialized, high-fidelity tasks via the regeneration menu.
The model is also becoming available in Search — including AI Mode and Lens — across mobile and desktop browsers, with expansion to 141 new countries and territories and support for eight additional languages.
Developers and enterprise users can access Nano Banana 2 in preview through AI Studio, the Gemini API, and Google Cloud’s Vertex AI platform. It is also now the default image generation model in Flow, available to all Flow users at no credit cost, and integrated into Google Ads to power creative suggestions during campaign development.
Strengthening AI content verification
Alongside the model’s launch, Google is reinforcing its content provenance tools to address growing concerns around generative media.
The company continues to pair its SynthID watermarking technology with interoperable C2PA Content Credentials standards. This combined approach provides clearer context about whether AI was used in a piece of content — and how it was used.
Since launching verification tools in November, Google reports that its SynthID verification feature in the Gemini app has been used more than 20 million times across multiple languages to identify AI-generated images, video and audio. C2PA verification support will soon be added to the Gemini app as well.
Expanding creative workflows
With Nano Banana 2, Google is positioning its Gemini ecosystem as a unified creative platform, offering users a choice between Nano Banana Pro for maximum factual accuracy and high-fidelity tasks, or Nano Banana 2 for rapid generation, precise instruction following and integrated search grounding.
As generative AI continues to evolve, Google’s latest release signals a push toward faster, smarter and more verifiable image creation tools embedded directly across its consumer and enterprise platforms.
