Google Releases Nano Banana 2.1 Image AI With Better Text And Consistency
The update targets the two problems that keep image models out of production workflows, text rendering and character consistency across edits, while keeping the Flash cost tier and adding search grounding.
Reporting from 2 sources: ASCII.jp, GIGAZINE.
Google announced Nano Banana 2.1, an updated image generation model built on Gemini 3.6 Flash. The model adds improved visual quality and text rendering at 1K, 2K, and 4K resolutions, fixes tiling artifacts in wide aspect ratios, supports fusion of up to 14 reference images, adds Google Search grounding, and offers configurable thinking levels. Known limits include weak page-length text rendering and imperfect character consistency.
The default output resolution stays at 1K, with 2K and 4K available. At those higher resolutions Google says it fixed tiling artifacts in the wide and panoramic ratios of 1:4, 4:1, 1:8, and 8:1, the formats where stitched output has been most visible.
Multi-image fusion accepts up to 14 reference images, holding consistency for up to four characters and fidelity for up to ten objects. Thinking levels can be set to minimal, medium, or high. Google lists remaining gaps in its own model card: small text, long paragraphs, page-length text, spatial relationships, and 3D reasoning.
Synthesized by Yomimono from the 2 cited sources below, including Japanese-language reporting where cited, then editorially reviewed before publishing.