Google's Gemini Flash-powered image generation and editing model that went viral for its speed, real-world knowledge, and AI-assisted editing capabilities.
Built on Gemini 2.5 Flash — generates images in seconds with minimal latency
Taps into Gemini's knowledge base and web grounding to render accurate, context-rich visuals
The Edit variant lets you transform existing images using natural language instructions
Nano Banana (Gemini 2.5 Flash Image) is Google DeepMind's fast and affordable image generation model that became a viral sensation upon its release in August 2025. Powered by the Gemini 2.5 Flash architecture, it brought a new level of accessibility to AI image creation — combining Gemini's real-world knowledge base with sub-10-second generation times at a fraction of the cost of premium models. It supports both text-to-image generation and AI-powered image editing through its companion Edit variant.
Unlike standalone diffusion models, Nano Banana is built directly on top of Gemini's multimodal foundation. This means the model doesn't just interpret your prompt as a string of keywords — it reasons about it. The model can draw on factual knowledge to render historically accurate scenes, generate correct infographics, visualize real-world recipes, or produce legible text within images. This world-knowledge grounding is what sets the Gemini image family apart from competing fast-generation models.
All images generated by Nano Banana are embedded with Google's imperceptible SynthID digital watermark, enabling AI provenance verification without degrading visual quality.
| Feature | Nano Banana | Nano Banana Edit |
|---|---|---|
| Input | Text prompt | Text prompt + source image |
| Best for | Generating new images from scratch | Modifying or transforming existing images |
| Typical use | Concept exploration, bulk generation | Retouching, style transfer, localized edits |
| Credits | 2 per image | 2 per image |
Nano Banana is the standard text-to-image variant. Give it a prompt and it returns a generated image — fast. It supports multiple aspect ratios from portrait (9:16) to landscape (16:9) and square (1:1).
Nano Banana Edit accepts an image alongside your text instruction. You can describe changes — "make it nighttime," "change the jacket to denim," "translate the text to Korean" — and the model applies them while preserving the overall composition. The Edit variant uses instruction-following to target specific elements rather than regenerating the entire image.
| Variant | credits |
|---|---|
| Nano Banana | 2 |
| Nano Banana Edit | 2 |
1 credit = $0.012
Quickly iterate on visual ideas and concepts before committing to a premium model
Leverage Gemini's world knowledge to generate accurate educational and data visuals
Describe changes in plain language and let the model apply them to your uploaded image
Generate large volumes of images affordably at just 2 credits per image
PopularBlack Forest Labs
Black Forest Labs' production-grade image generation model family delivering 4MP photorealistic output, multi-reference consistency across up to 10 images, and reliable text rendering — all in sub-10-second generation speeds.
From 3 credits
PremiumOpenAI
OpenAI's flagship natively multimodal image model with industry-leading instruction following, precise region-aware editing, and best-in-class text rendering — now up to 4x faster than its predecessor.
From 10 credits
Google DeepMind's leading text-to-image model delivering up to 2K resolution, superior text rendering, and diverse art styles — engineered for professional creative work.
From 2 credits
Start generating amazing content with Nano Banana today
Try Nano Banana Now