Google has launched Nano Banana 2, its latest AI image model, now available in the Gemini app and other services. This new model promises enhanced consistency for multiple characters and objects within a single image, improved texture rendering, and "vibrant" lighting.

- Figure 1 -
- Figure 1 -

Nano Banana 2 also expands output options, supporting resolutions from 512px to 4K widescreen. Google highlights its capabilities with example prompts, showcasing its proficiency in creating detailed scenes and artistic styles.

- Figure 2 -
- Figure 2 -

Starting immediately, Nano Banana 2 will be the sole image generation model across Gemini app, Search, AI Studio, Vertex AI, and Flow, replacing previous versions. It will power the image generation for Fast, Thinking, and Pro settings within the Gemini app and website.

- Figure 3 -
- Figure 3 -