Google has officially launched Nano Banana Pro, an advanced image generation model that enhances its predecessor with superior editing features, higher resolution options, and improved text accuracy. This new model, built on the recently introduced Gemini 3, is designed to provide professionals with greater control over image creation.
Nano Banana Pro stands out with its ability to generate high-fidelity images in resolutions up to 4K, compared to the earlier model’s maximum of 1024 x 1024 pixels. Users can manipulate various aspects of images, including camera angles, lighting, depth of field, and color grading. While the resolution improvements come at a cost—$0.139 for 1080p or 2K images and $0.24 for 4K images—the trade-off offers significant detail and customization.
Key Features of Nano Banana Pro:
– Generates images in 2K and 4K resolutions.
– Allows blending of up to 14 objects and maintains consistency for up to five individuals.
– Web searching capabilities enable users to look up relevant content, such as recipes, and generate related materials like flashcards.
– Offers control over scene lighting and focus for enhanced creative input.
– A demo app is available for users to explore these features.
The model will be integrated across a range of Google’s AI tools, with the Gemini app using Nano Banana Pro by default. While free-tier users can access limited image generation capabilities, those subscribed to Google AI Plus, Pro, and Ultra tiers will benefit from higher generation limits.
Additionally, developers can access Nano Banana Pro through the Gemini API, Google AI Studio, and the new IDE, Antigravity. The rollout will also include the implementation of SynthID, a tool to watermark and verify AI-generated content for authenticity. Looking ahead, Google plans to support C2PA content credential detection to further assist in content verification.
