Josh Woodward, Vice President of Google Labs, confirms that the model’s capabilities have developed significantly compared to the first version that appeared last August.
Woodward explained that “Nano Banana Pro” has become more advanced in producing graphs and creating slideshows, and it has the ability to handle up to 14 images or five different types of characters within the same image while maintaining visual consistency.
The new model continues the momentum created by the previous version, “Nano Banana,” upon its launch, after attracting more than 13 million new users to “Gemini” in its first month.
Users can experience “Nano Banana Pro” to a limited extent through free tools such as “Gemini” and “NotebookLM,” while subscribers to paid packages get higher usage limits.
The new model is superior to most image generators in its ability to integrate Arabic text within images accurately and linguistically soundly, which prompted many users to try its capabilities through social media platforms.
Google has also added a new feature to “Gemini” that allows checking any image uploaded by the user to determine if it is generated by artificial intelligence, in a step aimed at enhancing transparency and combating visual manipulation.
(CNBC)
