Nano Banana Pro

Nano Banana Pro (model ID gemini-3-pro-image) is the image generation and editing model built on Gemini 3 Pro, announced on November 20, 2025. It is the top tier of Google's Nano Banana family and the one aimed at work where an image has to be correct, not merely attractive: infographics, diagrams, product mock-ups and posters with readable, stylised typography — long the weakest point of image models. Two traits set it apart from ordinary generators. First, it can ground a picture in Google Search, so a chart or a card can be drawn from information fetched at generation time rather than from what the model happened to memorise. Second, it reasons about composition before drawing (a "thinking" pass), blends up to 14 input images and holds up to 5 characters consistent across a series — which is what makes it usable for repeatable, branded material instead of one-off pictures. It renders at 1K, 2K and native 4K, supports conversational multi-turn editing, and offers camera-style controls over framing and lighting. Every output carries an invisible SynthID watermark. Access is through the Gemini API, Google AI Studio and Vertex AI; billing is per generated image and rises with resolution.

▸Videos

No videos yet.

▸Reviews