Google Launches Nano Banana 2 Model With Faster Image Generation
Source: Slashdot
Overview
Google has launched Nano Banana 2 (Gemini 3.1 Flash Image), a faster, more realistic image‑generation model that is now the default across Gemini, Search, Lens, and Flow. According to TechCrunch, Nano Banana 2 retains many of the high‑fidelity characteristics of the Pro model while delivering images more quickly.
Image‑generation capabilities
- Resolution: Images can be generated at resolutions ranging from 512 px up to 4K, with support for various aspect ratios.
- Character consistency: The model can maintain consistency for up to five characters within a single workflow.
- Object fidelity: Up to 14 objects can be rendered with high fidelity, enabling richer storytelling.
- Complex prompts: Users can issue detailed, nuanced requests for image generation.
- Visual quality: Generated media feature more vibrant lighting, richer textures, and sharper detail.
Subscription plans
On Google’s higher‑tier AI plans—Google AI Pro and Google AI Ultra—subscribers can continue to use Nano Banana Pro for specialized tasks by regenerating images via the three‑dot menu.
Watermark and interoperability
All images created with Nano Banana 2 include a SynthID watermark, Google’s marker for AI‑generated content. These images are also interoperable with C2PA Content Credentials, a standard developed by an industry consortium that includes Adobe, Microsoft, Google, OpenAI, and Meta. Since the launch of SynthID verification in the Gemini app in November, the feature has been used over 20 million times.