Nano Banana Pro

Nano Banana Pro, built on Gemini 3 Pro, is Google's advanced image generation and editing model, combining reasoning with visual synthesis. It is a major upgrade over prior image generators, particularly in text rendering accuracy and multimodal composition. The model creates correctly rendered, legible text directly within images across multiple languages, supporting everything from short taglines to longer passages with varied fonts and calligraphy. It maintains visual consistency while blending up to 14 reference images and preserving the appearance of up to five people in complex scenes. Nano Banana Pro offers fine-grained editing controls, including localized edits, camera angle adjustments, color grading, lighting transformations, and focus changes, all driven by natural language prompts. It generates images at up to 4K resolution and draws on Gemini 3's real-world knowledge to produce context-rich infographics, diagrams, and grounded visualizations, with a 131K-token context window for extended visual reasoning.