Gemini Nano Banana 2.1 adds improved image editing and panoramic output
Gemini Nano Banana 2.1 is now generally available for image generation and conversational editing. Google reports improvements in visual quality, instruction following, character consistency and text rendering.
What changed
The model updates Nano Banana 2 while maintaining what Google calls Flash-level speed and cost efficiency. It improves character consistency across multiple editing turns and supports wide and panoramic aspect ratios of 1:4, 4:1, 1:8 and 8:1 across 1K, 2K and 4K resolutions. The previous `gemini-3.1-flash-image` model is deprecated.
Why it may matter for your work
Marketing and design teams could find it easier to create wide banners and keep characters consistent through revisions. Better text rendering and instruction following may reduce cleanup work on generated visuals.
What it can actually do
Generate images, edit them conversationally, render text and produce wide or panoramic images at multiple resolutions.
Limits to check
Generally available. The previous model is deprecated with no shutdown date announced; exact prices are not stated.
“**Gemini Nano Banana 2.1 generally available (GA)**: Released [Gemini Nano Banana 2.1](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1) (`gemini-nano-banana-2.1`), the latest high-efficiency image generation and conversational editing model.”From the linked source page