Nano Banana 2.1 is Google's newest Nano Banana image model (gemini-nano-banana-2.1). It is more efficient than Nano Banana Pro while delivering better image quality and stronger prompt adherence, with reliable text rendering and multi-subject composition. Describe the picture you want, or upload up to fourteen reference pictures to keep characters and objects consistent or to restyle them. If the result is not quite right, there is no need to re-upload anything: just type another instruction in the same conversation, such as "change the background to night" or "make the jacket red", and the previously generated image is reused automatically for continuous refinement; you can also upload other pictures in the same conversation as references for editing the previous result. The model thinks before it draws, so complex scenes and multi-step instructions come out more reliably. Good for social posts, product mock-ups, cover art and everyday creative work; switch to Nano Banana Pro when you need the most polished commercial output. Generated images are 1K resolution (longest side about 1024 pixels); the aspect ratio is decided automatically from your prompt or reference image, defaulting to about 1024x1024. Maximum total upload size per request: 512MB (all files and message content combined). Accepted image formats: jpeg, jpg, png. Maximum number of images: 14. Maximum size per image: 64MB. Maximum total image size per message: 64MB (text and history share the same request size limit; uploads close to the limit may still be rejected). Image dimensions: at least 200 pixels per side. Maximum image resolution: 36,000,000 pixels in total. Output content formats: Image Pricing: Medium-low Image output size: 1K (about 1024x1024 pixels). This module supports continuous conversations. AI can make mistakes. Please verify important information.