Google Unveils ‘Nano-Banana’ Image Model With Editing and Fusion Features

Google has announced the launch of Gemini 2.5 Flash Image, aka nano-banana, its latest image generation and editing model, now available through the Gemini API, Google AI Studio, and Vertex AI for enterprise.

The company said the model allows users to blend multiple images, maintain character consistency across edits, perform targeted transformations with natural language prompts, and leverage Gemini’s built-in world knowledge.

“When we first launched native image generation in Gemini 2.0 Flash earlier this year, you told us you loved its low latency, cost-effectiveness, and ease of use. But you also gave us feedback that you needed higher-quality images and more powerful creative control,” Google said in its announcement.

The model is priced at $30 per 1 million output tokens, with each image costing 1,290 tokens, or $0.039 per image.

Gemini 2.5 Flash Image supports fine-grained editing through natural language prompts. Users can apply changes such as blurring a background, erasing a stain on clothing, removing people from a picture, adjusting a subject’s pose, or adding color to black-and-white photos — all with a single instruction.

To showcase the new features, Google has released template apps within AI Studio, including tools for photo editing, character consistency, multi-image fusion, and educational interactions. Developers can remix or deploy these apps directly from the platform.

“We built a template app in Google AI Studio to demonstrate the model’s character consistency capabilities,” the team noted, adding that it allows developers to place the same character into different environments or generate consistent brand assets.

The update also includes integrations with OpenRouter.ai, which brings the model to its network of 3 million developers, and fal.ai, a generative media platform. Google confirmed that all generated or edited images will include an invisible SynthID watermark for transparency.

The model is currently in preview and will become stable in the coming weeks. Developers can access documentation and sample code to begin building.

“We can’t wait to see what you build with Gemini 2.5 Flash Image,” the company said, while adding that it is continuing work on improving long-form text rendering, factual accuracy, and character consistency.