# Nano Banana Pro

> Prompt to Image, Image to Image

- Canonical page: https://artifio.ai/models/nano-banana-pro
- Run it: https://artifio.ai/create/nano-banana-pro
- Modality: image to image
- Model brand: google
- Pricing: from about $0.090 per generation (exact cost shown in the workspace before you confirm; varies with selected options)
- Typical generation time: ~60s (catalogue estimate)
- Full pricing table: https://artifio.ai/pricing/models

## About Nano Banana Pro

Nano Banana Pro is Google DeepMind's Gemini 3 Pro Image model, released on November 20, 2025 as the higher-end successor to the original Nano Banana (Gemini 2.5 Flash Image). It was announced in the same week as the Gemini 3 language model it is built on, and it trades some speed for reasoning-driven composition, stronger text rendering, and studio-style editing controls.

This page covers the image-to-image mode: editing, restyling, and compositing from supplied reference images. On artifio.ai it runs next to 100+ other models in one workspace from a single pay-per-generation wallet.

## Features

- Accepts up to 14 reference images in one request and can hold the likeness of up to 5 people consistent across the composition.
- Google's developer guide describes combining up to 6 high-fidelity object inputs in a single output, useful for loading a whole style guide of logos, palettes, and product shots.
- Studio-style local controls let an edit change camera angle, focus and depth of field, color grading, and scene lighting, including day-to-night relighting and added bokeh.
- Outputs at 1K, 2K, or 4K resolution across a wide aspect-ratio range, from 1:1 and 9:16 through cinema formats like 2.39:1 up to 4:1 banners.
- Translates and localizes text inside an existing image, redrawing signage or packaging copy in another language while keeping the design.
- Optional grounding with Google Search pulls real-time information into an edit, and every output carries a SynthID watermark.

## What people use it for

- Brand and marketing work that composites many reference assets into one on-style visual.
- Localizing a finished design for international markets by translating the text baked into the image.
- Turning sketches or product photos into polished renders and 3D-styled mockups.
- Photo post-production requests such as relighting, refocusing, or regrading a shot without manual masking.
- Multi-person scenes, like team or family composites, where every face must stay recognizable.

## Reported strengths

- DeepMind's model page reports leading Elo scores for image editing among competing models at release.
- In-image text rendering error rates mostly under 10 percent across languages, per DeepMind's published comparison, which made legible paragraph-length text practical.
- The 14-reference-image budget and 5-person consistency give it unusually large compositing capacity.
- Reasoning inherited from Gemini 3 Pro helps it follow long, multi-constraint edit instructions accurately.

## Reported limitations

- Google's own developer post says it comes with higher cost and latency than Gemini 2.5 Flash Image, so it suits final assets more than rapid iteration.
- Free and lower-tier Gemini surfaces apply a visible watermark to outputs; Google removes it only for its top subscription tier, and SynthID is embedded regardless.
- On Google's consumer apps, free users get a limited quota before requests fall back to the older Nano Banana model.
- Since February 2026 Google itself has defaulted most surfaces to the newer Nano Banana 2, positioning Pro as a specialized rather than everyday choice.

## Sources

1. Nano Banana Pro: Gemini 3 Pro Image model from Google DeepMind (Google (The Keyword)): https://blog.google/innovation-and-ai/products/nano-banana-pro/
2. Gemini 3 Pro Image – Nano Banana Pro (Google DeepMind): https://deepmind.google/models/gemini-image/pro/
3. Developers can build with Nano Banana Pro (Gemini 3 Pro Image) (Google (The Keyword)): https://blog.google/innovation-and-ai/technology/developers-tools/gemini-3-pro-image-developers/
4. Google releases Nano Banana Pro, its latest image-generation model (TechCrunch): https://techcrunch.com/2025/11/20/google-releases-nano-banana-pro-its-latest-image-generation-model/

---

About Artifio.ai: 100+ AI image, video, and audio models in one workspace with a single shared wallet — no per-model subscriptions. This is the markdown rendition of https://artifio.ai/models/nano-banana-pro for AI assistants and crawlers; the HTML page is canonical.