Introduction
Nano Banana Pro is an AI image generation model available on invideo, powered by Gemini 3.0 Pro and GemPix 2 diffusion. It generates and edits photorealistic images up to 4K, with strong character consistency, precise text rendering, and reasoning-aware output. It is the default image model on Agent One Pro.
This article covers how to access Nano Banana Pro, creation modes, prompt best practices, and available settings.
How to get started
From the homepage, click Generative models → Image models → See all → select Nano Banana Pro
Upload a reference image to edit, or start from a text prompt alone
Enter a detailed description of the image you want to create
Preview your result, refine with a follow-up prompt, and download
Prompt best practices
Nano Banana Pro responds well to prompts that describe subject, environment, lighting, and style together - the more specific, the more precise the output.
Example: Close-up portrait of a man in a navy suit standing in a glass office at golden hour, warm backlight, shallow depth of field, editorial photography style.
💡 Tips for better results | Why it helps |
Describe lighting and mood explicitly | Nano Banana Pro applies scene-wide relighting with coherent shadows and highlights |
Specify camera angle in your prompt | Wide, medium, close-up, and top-down angles can all be generated from the same scene description |
Include text you want rendered in the image | Nano Banana Pro handles multilingual text accurately - describe font style and placement |
Use image editing for targeted changes | Describe only what should change - the model preserves everything else intact |