Overview
- Nano Banana 2 becomes the default image generator in the Gemini app’s Fast, Thinking and Pro modes, in Search via AI Mode and Lens, and in Flow, with availability expanding across 141 countries.
- The new model blends faster generation with Pro‑level capabilities such as improved instruction following, accurate text rendering and translation, and real‑time web grounding for more specific, factual renders.
- Outputs range from 512px to 4K across multiple aspect ratios, while the model maintains character consistency for up to five characters and preserves fidelity for up to 14 objects, with richer lighting, textures and detail.
- Developers can access the model in preview through the Gemini API, AI Studio, Vertex AI, Antigravity and the Gemini CLI, supporting consumer, enterprise and production use cases.
- All images carry Google’s SynthID watermark and interoperable C2PA Content Credentials, and Nano Banana Pro remains available to Google AI Pro and Ultra subscribers for specialized high‑fidelity tasks.