Google DeepMind DeepMind
code
Build with Gemini
spark
Chat with Gemini

Nano Banana 🍌

State-of-the-art image generation and editing models, built on Gemini

Try in Gemini
Build with Nano Banana

Nano Banana Pro 🍌

Built on Gemini 3. Create and edit images with studio-quality levels of precision and control

Try in Gemini
Build with Nano Banana Pro

Nano Banana 🍌

Gemini 2.5 Flash Image lets you bring your imagination to life using text and image prompts.

Try in Gemini
Build with Nano Banana

Imagine almost anything – then create it. Generate detailed, playful, realistic, or whimsical images. Or anything in-between.

The Gemini Image model uses deep language understanding to capture the nuance of your prompts — bridging the gap between what you say and what you envision.

Capabilities

Multimodal understanding

Upload images and share text instructions with Gemini to create complex and detailed images.

Conversational inputs

Use everyday language while creating images, and keep the conversation going to refine what the model generates.

Real-world knowledge

Generate images that follow real-world logic, thanks to Gemini’s advanced reasoning capabilities.

Model family

Gemini Image models are natively multimodal, and respond effectively and efficiently to even the most detailed prompts.

Nano Banana Pro (Gemini 3 Pro Image)

Create and edit images with studio-quality levels of precision and control.

Learn more

Try Nano Banana (Gemini Image)