Nano Banana Pro (Gemini 3 Pro Image) for developers
Google DeepMind released Nano Banana Pro, an image generation and editing model built on Gemini 3 Pro, with more accurate text rendering, Google Search grounding, fine camera and lighting control, and up to 4K output.
What happened
Google DeepMind released Nano Banana Pro (Gemini 3 Pro Image) in paid preview through the Gemini API, Google AI Studio and Vertex AI. It follows Nano Banana (Gemini 2.5 Flash Image) from a few months earlier.
The technical details
From the post:
- built on Gemini 3 Pro, for higher-fidelity generation and editing
- more accurate text rendering in images
- grounding with Google Search, to retrieve facts relevant to the prompt
- control over lighting, camera, focus and colour grading, and over composition
- 2K and 4K output
- available to coding agents in Google Antigravity (e.g. generating UI mockups), and integrated by Adobe and Figma
Why it matters
Image models are converging with language models: the same backbone that reasons and searches also draws. Text rendering, a classic weak point, is also what Qwen-Image targeted (August 2025 paper summary).
#genai#image-generation#google
Sources
- Build with Nano Banana Pro, our Gemini 3 Pro Image model — Google DeepMind
This is a summary written from the linked public sources. Figures and numbers are as reported there.