Google has unveiled Nano Banana 2, the latest version of its image generation system and technically known as Gemini 3.1 Flash Image, positioning it as the new default model across the Gemini app and related services. The update delivers faster generation speeds while retaining high-fidelity output, supporting resolutions from 512 pixels to 4K and enabling complex prompts with improved lighting, textures, and detail. The model can maintain consistency across up to five characters and numerous objects, enhancing visual storytelling capabilities.
Nano Banana 2 will power image creation in Gemini’s Fast, Thinking, and Pro modes, as well as Google Search features such as Lens and AI Mode across more than 140 countries. The model is also integrated into Google’s Flow video tool and developer platforms. All generated images include SynthID watermarking and compatibility with C2PA content credentials to signal AI-generated media.
