Google's new Nano Banana 2.1: improved AI images

Google has announced the launch of Nano Banana 2.1, an advanced model for generating and editing images. According to Google, this new version offers significant improvements in visual design, mask-based editing, and subject consistency. This is intended to enable users to create more natural images that maintain consistency across various contexts and edits.

The rollout of Nano Banana 2.1 began on October 6 across various platforms, including the Gemini app, AI Mode in Google Search, and Google Ads. This gradual implementation ensures that both consumers and business users can experience the benefits of this revamped model. The new features are particularly important for users who want to make modifications to their images without having to redesign the entire composition.

A key improvement in Nano Banana 2.1 is the ability to adjust specific parts of an image. This allows users to make targeted adjustments to, for example, a background or a specific object while keeping the main subject intact. This is especially relevant for professionals looking to optimize product photos by varying the environments without altering the product itself.

The new capabilities of Nano Banana 2.1 are integrated into both consumer and business applications, including Google AI Studio for developers and the Gemini Enterprise Platform for business users. This offers different possibilities depending on the environment in which Nano Banana 2.1 is used. With these updates following the previous versions, the model can now generate new images as well as further refine existing edits with greater attention to recognizability.

Read the full article from AI Insider.