Hey there, thanks so much for your interest in this guide. My name is Jo Lambadjieva and I am an AI in Ecommerce expert. I train teams how to use AI in their different business use cases and my team also builds systems that automate certain or all parts of a process. If you enjoy this SOP and you would like to find out when I post more new SOPs, feel free to join my WhatsApp group.
And don’t worry, it’s a mute group - you won’t get 100s of messages every day :)

1. MODEL OVERVIEW
Core Specifications
- Model Name: Gemini 3 Pro Image (branded as Nano Banana Pro / Nano Banana 2)
- Capabilities: Image generation and editing (text-to-image, image-to-image, multi-image fusion)
- Resolution Options: 1K, 2K, 4K (higher resolution uses more credits)
Key Features
- Multi-Image Composition: Combine up to 14 images into one composition
- People Consistency: Maintain consistent appearance for up to 5 people across edits and angles
- Text Quality: Sharp, multilingual text rendering including complex scripts (Czech, Korean)
- Live Context Integration: Connects to Google Search and Google Weather for fact-based visuals and infographics with real data
- Watermarking: Built-in SynthID and C2PA metadata for content authenticity
Platform Access
- Gemini app (Create images → "Thinking" model)
- Search AI Mode
- Google Ads, Slides, Vids, NotebookLM
- AI Studio, Gemini API, Vertex AI
- Third-party platforms (Fal.ai, GlobalGPT, etc.)