Google Pics Upgrades the Nano Banana 2.1 Model: More Detailed Image Generation, More Accurate Image Editing
IT Home, November 17 news: Google yesterday (November 16) released an official Workspace update announcement, announcing that its image tool Google Pics has been upgraded to the Nano Banana 2.1 model, further improving the image generation and editing experience.
Regarding rollout, Google stated that for Rapid Release and Scheduled Release users, deployment will be completed within the next 1–3 days, and it mainly applies to the following subscribers:
| User category | Covered subscriptions or add-ons |
|---|---|
| Business | Business Standard, Business Plus |
| Enterprise | Enterprise Standard, Enterprise Plus |
| Individual subscriptions | Google AI Plus, Google AI Pro, Google AI Ultra |
| Education add-on | Google AI Pro for Education |
| Other add-ons | AI Expanded Access |
This model upgrade has no separate admin toggle and no user-side switching setting. Google Pics is enabled by default, but administrators can still disable the service at the domain, organizational unit (OU), or group level.
This upgrade focuses on solving issues such as images "not being detailed enough and edits easily going off track." According to Google's announcement, the new model will improve image detail, natural lighting, and material texture rendering; during partial or full edits, it will better preserve the original image content and reduce unnecessary changes to surrounding people, backgrounds, and brand elements.



Text within images is also a key focus of this improvement. Google stated that when the new model generates or modifies text in images, the glyphs and layout will be clearer and more accurate, while maintaining processing speed similar to the previous version. In addition to the standalone Pics app, users who invoke Pics to edit images in Google Docs and Google Slides will also receive this update.
IT Home previously reported in October that Nano Banana 2.1 was released on October 7, achieving all-around improvements, with particularly notable progress in visual design, mask-based image editing, and subject consistency.
Related Articles
- The best AI assistant for app side hustles: Google launches a series of tools targeting the most troublesome monetization step
- A key step toward AI taking over phones: Google Gemini automation app list exposed, currently 134 in total
- Letting AI reply directly to users in the UI: Google open-sources the cross-platform protocol A2UI 1.0, and ByteDance has already adopted it
- Google Gemini launches memory summaries, allowing users to view / edit / delete personal information remembered by AI
- Farewell to the knowledge cutoff date: Google teaches AI to "sleep," learning on the job without forgetting old knowledge
- Less than two years after launch, Google's AI programming assistant Jules will gradually cease service