Google releases Nano Banana Pro, its latest image generation model

Google has announced a significant enhancement to its image generation capabilities with the introduction of the Nano Banana Pro model. This latest iteration is equipped with advanced features that enable users to create more intricate images, improve text accuracy, and explore web resources seamlessly. Built on the foundation of Google’s cutting-edge large language model, Gemini 3, released just days ago, Nano Banana Pro is said to surpass its predecessor, Nano Banana. Among its standout features are the ability to generate images in 2K and 4K resolutions, a substantial upgrade from the previous model’s maximum of 1024 x 1024 pixels. Users can now expect enhanced detail, with the option to manipulate various aspects of their images, including camera angles, lighting, depth of field, and color grading. Despite these advancements, Google notes that Nano Banana Pro comes with increased costs and slower processing times. While the original model charged $0.039 for each 1024px image, the new version will set users back $0.139 for 1080p or 2K images and $0.24 for 4K images. Furthermore, the model allows for the incorporation of six high-fidelity shots and blending of up to 14 objects within a single image while maintaining consistency for up to five individuals. To allow users to experience these features firsthand, Google has launched a demo application showcasing Nano Banana Pro’s capabilities. The model will be integrated across Google’s AI tools, with the Gemini app utilizing it for image generation by default. Users on the free tier will have access to a limited number of image generations before being reverted to the older Nano Banana model. For those subscribed to Google AI Plus, Pro, and Ultra tiers, higher generation limits will apply, although specific thresholds have yet to be disclosed. Additionally, these subscribers will gain access to Nano Banana Pro through Notebook LM and in the company’s video tool, Flow. Google is also incorporating the model into its Workspace offerings, including Google Slides and Vids. Developers interested in leveraging Nano Banana Pro can access it through the Gemini API, Google AI Studio, and the new IDE, Antigravity. To ensure transparency regarding AI-generated content, Google has integrated SynthID technology for watermarking and detecting AI-created images within the Gemini app. Users can upload images to verify whether they have been generated or altered by Google’s models. However, the company has yet to clarify its plans regarding compatibility with other AI watermarking standards like C2PA.