Google unveiled Gemini 2.5 Flash Image (aka nano-banana), the company’s latest image generation and editing model. The model is designed to excel at maintaining character consistency, adhering to visual templates, enabling targeted transformations, and making precise local edits using natural language.
This latest image generation and editing model tops the LMArena’s Image Edit Arena leaderboard, outperforming FLUX.1 Kontext model in terms of voting and score. For wider availability, Google has integrated it into its Gemini app, allowing users to create their perfect picture.
Demonstrating various use cases of the model, Google has listed certain capabilities for users to try out:
- You can upload a picture of yourself or your pet and try changing the costume or location in the image. The model is expected to offer reimagined outputs while keeping the subject’s appearance consistent in every situation.
- The new model also lets you upload multiple photos and blend them for a brand-new scene through natural language query.
- The model also offers you multi-turn editing capability, meaning you can keep editing the images Gemini makes.
- Mix up designs: Apply the style of one image to an object in another. You can take the color and texture of flower petals and apply it to a pair of rain boots or design a dress using the pattern from a butterfly’s wings.
Availability
The general audience can try this model via the Google Gemini app now.
It is also available via the Gemini API and Google AI Studio for developers and Vertex AI for enterprise. Gemini 2.5 Flash Image is priced at USD 30.00 per 1 million output tokens, with each image being 1290 output tokens (USD 0.039 per image).
Note: All images created or edited in the Gemini app include a visible watermark, as well as our invisible SynthID digital watermark, to clearly show they are AI-generated.