Google Launches Nano Banana 2.1 Image Model Across Gemini and AI Studio
Google's new image generation and editing model adds mask-based editing, up to 14 reference images, and configurable Thinking levels as it rolls out to Gemini, Flow, and Ads.
Google announced the launch of Nano Banana 2.1, its latest image generation and editing model, which is rolling out today across the Gemini app, AI Mode, AI Studio, Flow, Stitch, Google Ads, and the Gemini Enterprise Platform.
According to Android Authority, the update targets visual design, mask-based editing, and subject consistency. Google says visual quality and realism improve across 1K, 2K, and 4K output resolutions, with 1K remaining the default.
Nano Banana 2.1 also addresses tiling artifacts on wide and panoramic aspect ratios at 2K and 4K resolutions, and improves text rendering and infographic layout accuracy. The model supports multi-image fusion with up to 14 reference images, as well as grounding with Google Web and Image Search.
Thinking levels are now configurable at minimal, medium (default), and high. Google describes Nano Banana 2.1 as a more efficient counterpart to Nano Banana Pro.
Google previously released Nano Banana 2.0 in February 2026, which enabled image generation at up to 4K resolution.
Quick answers
Where is Nano Banana 2.1 available?
It is rolling out today across the Gemini app, AI Mode, AI Studio, Flow, Stitch, Google Ads, and the Gemini Enterprise Platform.
What output resolutions does Nano Banana 2.1 support?
It supports 1K, 2K, and 4K, with 1K as the default.
How many reference images can Nano Banana 2.1 use?
It supports multi-image fusion with up to 14 reference images.