Google launches nano banana 2.1, enhancing visual design and image editing capabilities

Google has released Nano Banana 2.1, an updated version of its AI image generation and editing model. The upgrade focuses on improvements in visual design, mask-based editing, and subject consistency. This follows the earlier release of Nano Banana 2, which was also known as Gemini 3.1 Flash Image. Nano Banana 2.1 builds on these capabilities, offering better visual composition and higher-quality outputs. It also enhances subject consistency, ensuring that the same person or object remains visually consistent across multiple generated images. The model is now available across several platforms, including Gemini, Google Search, and Google AI Studio. For developers, Nano Banana 2.1 is accessible with the model ID gemini-nano-banana-2.1, supporting text, image, audio, and video inputs. OpenAI's ChatGPT Images 2.5 remains the leading image generation model, while Microsoft's MAI-Image-2.6 was released in August 2026.