Google Releases Nano Banana 2.1 with Enhanced Image Quality

Google has unveiled Nano Banana 2.1, the latest iteration of its image generation and editing model, marking a significant upgrade in visual quality and consistency. The new version enhances visual design, mask-based editing, and subject consistency, making it a more efficient alternative to Nano Banana Pro. Key improvements include better text rendering, infographic layout accuracy, and support for multi-image fusion, allowing up to 14 reference images for character and object consistency.

Nano Banana 2.1 also addresses tiling artifacts on wide and panoramic aspect ratios at 2K and 4K resolutions, ensuring smoother outputs. The model supports configurable thinking levels, minimal, medium (default), and high, and integrates grounding with Google Web and Image Search for more accurate results.

The update is now rolling out across several Google services, including the Gemini app, AI Mode, Google AI Studio, Google Flow, Stitch by Google, Google Ads, and the Gemini Enterprise Platform. The previous version, Nano Banana 2.0, was released in February and introduced 4K resolution capabilities.