Cinematic street portrait at night
A moody, film-still portrait lit by neon signs and wet asphalt reflections. One of the most reliable looks for social media covers.
Prompt library, guides & examples
Nano Banana 4 turns plain-language prompts into stunning, photorealistic images — with character consistency, precise editing and legible text rendering. Learn how to get the most out of it.
Nano Banana 4 is the community nickname for the fourth generation of Google's Gemini-powered image generation and editing model. It builds on the viral success of the original Nano Banana with sharper detail, stronger prompt adherence and dramatically better multi-step editing.
You describe what you want in everyday language — a scene, a product shot, a portrait, an edit to an existing photo — and the model renders it in seconds. No layers, no masks, no complicated parameters.
Six capabilities that set Nano Banana 4 apart from earlier image models.
Generate photorealistic scenes, illustrations and concept art from a single sentence, with accurate lighting and composition.
Upload a photo and edit it by talking: remove objects, swap backgrounds, change outfits or restyle the whole shot.
Keep the same face, character or product identical across many generations — ideal for storyboards and brand assets.
Blend several reference images into one coherent result: place your product into a new scene or merge styles.
Posters, logos, UI mockups and infographics with clean, correctly spelled text directly in the image.
Crisp 2K and 4K output with consistent detail, ready for print, e-commerce and social media.
A few popular looks from the community — each card shows the kind of prompt that produces it.
Copy one of these community favorites and try it right away.
A moody, film-still portrait lit by neon signs and wet asphalt reflections. One of the most reliable looks for social media covers.
E-commerce ready hero shot on a seamless background with controlled studio lighting. Works for almost any product.
The viral effect: turn any person or character photo into a boxed collectible figurine with desktop packaging scene.
Repair scratches, fix fading and add historically plausible color to family photos from decades ago.
Nano Banana 4 is the community nickname for the fourth generation of Google's Gemini image generation and editing model. The name "Nano Banana" started as the anonymous codename the model used on testing leaderboards and stuck after it went viral. Generation 4 focuses on sharper detail, better prompt adherence, consistent characters across images and reliable text rendering.
You can use it through the Gemini app (web and mobile), Google AI Studio, or programmatically via the Gemini API. In the Gemini app simply choose the image generation option and type your prompt. Developers can call the model through Google AI Studio with an API key.
There is a free tier with a daily limit of image generations in the Gemini app. Paid Google AI subscriptions raise the limits significantly and unlock the highest quality settings. API usage is billed per image.
Google's generative AI terms generally allow you to use the images you generate, including for commercial purposes, provided you comply with the usage policies. You are responsible for making sure your prompts and outputs don't infringe third-party rights (trademarks, celebrity likeness, copyrighted characters). Always review the current terms before commercial use.
Start with a proven prompt from the library, then follow the guides to refine your results.
Explore the prompt library