November 21st.GoogleNew image generation and editing model officially launched Nano Banana Pro (Gemini 3 Pro Image) The model, based on the Gemini 3 Pro architecture, is called “unprecedented control, perfect text replicating and enhanced world knowledge reserves” and transforms user ideas into “studio-equality” designs. This update represents another important leap in Google's image generation, compared to the original model released in September this year, which was rededicated by the production of 3D overwriting。
As of this date, Nano Banana Pro is open for free testing for users worldwide. The user simply needs to login to Gemini applicationSelect the " Generation image " function and switch to the " Thinking " mode to experience this latest model。
According to Google, Nano Banana Pro has done well in processing complex information, producing information graphs with rich context, visualizing real-time data such as weather, sports events, etc。
A major breakthrough in the model is its text replicabilityI don't know. Nano Banana Pro can generate more detailed and text-specific images and support the production of text content in different styles, fonts and languages. Nano Banana Pro is able to render it clearly and accurately in the image, whether it is short or long text. This feature makes it extremely practical and suitable for producing posters or invitations in multiple languages. In addition, the model has a strong synthesis capability, supporting the integration of up to 14 image materials and up to 5 individual objects in one image。
According to 1AI, Nano Banana Pro introduced more advanced creative control options for editing functions. Users can not only make local selection and editing of images, but can also adjust the camera angle, add back-to-back Bokeh effects, change focus, perform professional colour classification (Color Grading), or even freely switch the light from day to night. In terms of output specifications, the model supports multiple long-width ratios, with a maximum of 4K resolution high-resolution high-resolution images。
It is noteworthy that all images generated or edited through Nano Banana Pro will be embedded in C2PA metadata. As industry norms evolve, this initiative aims to make it easier for users to identify generated AI content and deep forgery (Deepfakes) in search results and social media. This week, TikTok also announced that C2PA metadata will be used to add invisible watermarks to the content of AI。
However, Google also noted that although the quality of the Nano Banana Pro image had improved significantly, its production rate had decreased and its cost of use had been higher: the original Nano Banana single 1024px image generation cost was $0.039 (IT House Note: the current rate is approximately $0.28), while the cost of Nano Banana Pro ' s generation of 1080p/2K image had risen to $ 0.139 (the current rate is approximately $0.99) / Chang, while the 4K image was $0.24 (the current rate is approximately $1.7) / Chang。
Currently, the free version of the Nano Banana Pro has a limited use limit, while Google AI Plus, Pro and Ultra have more quota for subscribers. In addition, Google AI Pro and Ultra subscribers in the United States can use the model in the "AI mode" of the search function, and the Global NotebookLM scientific assistant users can call directly。
Currently, Nano Banana Pro is gradually integrating into Google's many mainstream AI tools:
- Gemini application: by default enabled Nano Banana Pro to generate images; free users can generate a limited number of images, which will automatically return to Nano Banana when the amount is exhausted
- Google AI Plus/ Pro / Ultra subscriber: has a higher generation quota (specific upper limit unpublished) and can call the model in Notebook LLM
- Search: AI Pro and Ultra subscribers in the U.S. region can use the model in "AI mode"
- Video Tool Flow: Ultra subscribers only
- Google Workspace: The use of Nano Banana Pro in Slides and Vids is now supported。
For the developers, the model is open for access to Gemini API, Google AI Studio and Google's new Integrated Development Environment (IDE) Antigravity。