NANO BANANA

Google's Advanced Image Generation & Editing Model Built on the Gemini 3 Family

Precise, High-Quality Images

Nano Banana models apply deep reasoning capabilities to fully understand your prompt before generating an image. They offer unprecedented creative control for generating stunning, high-fidelity images up to 4K visuals.

Built on the Gemini 3 Pro Image (Nano Banana Pro) and Gemini 3.1 Flash Image (Nano Banana 2) architectures, these models feature seamless multimodal generation, and are powered by real-time information from web search to deliver accurate and contextually relevant visual results.

4K
Max Resolution
Real-Time
Web Search Data
10+
Multilingual Text
SynthID
Watermarking & C2PA

Technical Specifications

  • memory
    Models: Gemini 3.1 Flash Image (Nano Banana 2) & Gemini 3 Pro Image (Nano Banana Pro).
  • aspect_ratio
    Supported Ratios: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9.
  • collections
    Multimodal Inputs: Mix up to 14 reference object images or document inputs up to 50MB.
  • translate
    Multilingual Text Generation: Supports state-of-the-art multilingual text generation in over 10 languages directly within images.

Safety & Trust

Nano Banana models are designed with responsible AI principles at their core, ensuring that all generated content is verifiable and traceable.

StandardC2PA Content Credentials
➔
Embeds metadata describing the origin and history of the generated media.
WatermarkSynthID
➔
Imperceptible digital watermarks embedded directly into the pixels of images.