Google has unveiled Nano Banana 2.1, an advanced AI image generation and editing model built upon Gemini 3.6 Flash. This new model reportedly outperforms its predecessors in various image generation and editing tasks, including the creation of detailed infographics and consistent photo editing. Nano Banana 2.1 also supports prompts with up to one million tokens and is being integrated across various Google products, though the company acknowledges areas for further improvement, particularly with small text generation and factual accuracy. AI
IMPACT Sets new SOTA on image generation and editing benchmarks, potentially influencing future multimodal model development.
RANK_REASON Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=1 ai=1.0]
- android
- Flow
- Gemini
- Gemini 3.6 Flash
- Gemini 3 Flash
- Google Ads
- Google AI Studio
- Google Books
- HubSpot
- Larry Page
- Mindstream
- Nano Banana 2
- Nano Banana 2.1
- Nano Banana Pro
- OpenAI
- Search AI Mode
- Sergey Brin
- The Whatbox
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →