Nano Banana Pro: Google’s new image AI offers 4K images and product mock-ups

Google is on a roll right now, having shaken off the ChatGPT threat and delivering hit after hit. Shortly after the launch of Gemini 3 Pro, which immediately claimed the top spots on the LLM charts, comes the release of “Nano Banana Pro.” This is the improved version of Google’s in-house image generator, which already made waves this year—not least because users could generate images showing themselves alongside their childhood selves.

Google unveiled Nano Banana Pro (aka Gemini 3 Pro Image) today, Thursday—a new AI model for image generation and editing based on Gemini 3 Pro. According to Google, the model promises to transform “your visions into studio-quality designs” with improved control, precise text rendering, and expanded factual knowledge. The launch rolls out globally on November 20, 2025, in the Gemini app, where users can select the “Create Images” function with the “Thinking” model. The tool is available for free, though with limited quota for free-tier users.

Nano Banana Pro builds on the original Nano Banana, which Google launched roughly three months ago and went viral thanks to hyperrealistic 3D figures. The Pro version significantly expands capabilities: the model combines up to 14 images in a single composition while maintaining consistency across up to five people.

Thanks to Gemini 3’s reasoning capabilities, it creates contextual infographics and diagrams based on real-time information like weather or sports results. The system taps into Google Search’s knowledge base and visualizes complex data.

Text in Multiple Languages and 4K Resolution

Text rendering marks a major breakthrough: Nano Banana Pro renders readable text directly in the image—from short slogans to longer paragraphs. Gemini 3’s multilingual capabilities enable text generation and translation across languages, simplifying content localization. Users can create mockups and posters with detailed text, various textures, fonts, and calligraphy. The model supports resolutions up to 4K in different aspect ratios.

Editing functions offer studio-level control: users select and edit individual image areas, adjust camera angles, add bokeh effects, shift focus, perform color corrections, or transform lighting—say, from day to night. These precise control options position the tool for professional applications, from prototyping through product design to marketing assets.

Rollout Across Google Products and Transparency Features

Nano Banana Pro rolls out incrementally across the Google ecosystem. In Google Ads, global rollout begins in eight languages: German, English, Spanish, Dutch, French, Italian, Portuguese, and Japanese. Workspace customers gain access in Google Slides and Vids. Developers can leverage the model via Gemini API, Google AI Studio, Vertex AI, and Google Antigravity. In the US, it’s available in Google Search’s AI Mode for AI Pro and Ultra subscribers; globally, it’s also in NotebookLM. Creatives get access through Flow, Google’s AI tool for film production—but only with an AI Ultra subscription.

Google integrates transparency mechanisms: all images created or edited with Nano Banana Pro receive C2PA metadata and the invisible SynthID watermark. Users can now upload an image to Gemini and directly ask whether it was generated with Google AI—SynthID technology provides the answer. Additionally, Google marks images from free and AI Pro users with a visible watermark (the Gemini symbol). AI Ultra subscribers receive images without visible watermarks to avoid disrupting professional workflows. Pricing remains tiered: free users get limited quota, while AI Plus, Pro, and Ultra subscribers benefit from higher limits.