< Back to all clusters
[TECHNOLOGY] · United States · 24 sources

started · updated

Google launches Nano Banana 2.1 AI image model

Google has launched Nano Banana 2.1, an updated AI image generation and editing model based on Gemini 3.6 Flash. The new model introduces significant improvements in visual design, mask-based localized editing, and subject consistency. It can maintain the appearance of up to four characters and ten objects across multiple images or edits, and can process up to 14 reference images to guide generation.

Technical enhancements include improved text rendering within images, better infographic accuracy, and the elimination of tiling artifacts in ultra-wide panoramic formats (such as 8:1). The model supports resolutions of 1K, 2K, and 4K. Additionally, it features configurable “Thinking” levels—minimal, medium, and high—to allow users to balance processing speed with output quality.

For developers, Google has reduced API costs for image output by approximately 50% compared to the previous Nano Banana 2 model. The update is being rolled out across the Google ecosystem, including the Gemini app, Google Search AI Mode, Google Ads, Google AI Studio, Flow, and Stitch. Nano Banana 2.1 is positioned as a high-efficiency counterpart to the more powerful Nano Banana Pro.

Entities

Alphabet · Gemini · Gemini 3.6 Flash · Google · Google AI Studio · Google DeepMind · Nano Banana 2.1 · Robby Stein

Claims

What the coverage asserts, and how many sources carry each claim.

Sources

Nano Banana 2. 1 上线!超全AI 生图变化分享,Flux Art 新能力观察_天极网 [news.yesky.com]