Latest models
- Nano Banana 2.1 (October 6, 2026) Current
Image model built on Gemini 3.6 Flash that takes text and images in and outputs images, with a model card listing the Gemini app, Google AI Studio, the Gemini API, Search AI Mode, Google Ads, Flow and Stitch. Source: Google DeepMind model card ↗ - Nano Banana 2 (February 26, 2026) Current
Google's image model that combines Nano Banana Pro capabilities with Gemini Flash speed, available in the Gemini app, Search and the Gemini API. Source: Google blog ↗
Checked October 15, 2026. See the full AI model tracker.
What we like
- Google says it keeps the resemblance of up to five characters and the fidelity of up to 14 objects in one workflow
- Output from 512px up to 4K with control over aspect ratio
- Built into Google products you may already use
Watch out for
- Capabilities and limits vary by product and plan
- Google's claims are its own; test with your own images
- Less distinctive as a house style than Midjourney
Nano Banana 2 is Google DeepMind’s image generation and editing model, announced on February 26, 2026. Google describes it as combining the advanced features of Nano Banana Pro with the speed of Gemini Flash.
What is current
Google DeepMind published the model card for Nano Banana 2.1 on October 6, 2026. It is based on Gemini 3.6 Flash, accepts text and images, and lists the Gemini app, Google AI Studio, the Gemini API, Search AI Mode, Google Ads, Flow and Stitch as channels. Check each Google product to see which version it uses.
Nano Banana 2 is available in the Gemini app and Google Search and through the Gemini API and Vertex AI. Google also introduced Nano Banana 2 Lite as its fastest, most cost-efficient Gemini image model. See the model tracker.
What Google highlights
- Knowledge from Gemini, with real-time information and images from web search to render specific subjects more accurately.
- Subject consistency: Google says it can keep the resemblance of up to five characters and the fidelity of up to 14 objects in one workflow.
- Control over aspect ratio and resolution from 512px to 4K.
- SynthID and C2PA Content Credentials to help identify AI-generated images.
Who should use it
Anyone working in Google’s tools, and creators who need the same character or object across several images, such as storyboards. Read more in consistent characters with AI.