SMRTR AIAug 26, 2025Ars Technica

Google improves Gemini AI image editing with “nano banana” model

SMRTR summary

Google's DeepMind has added the "nano banana" model to the Gemini app, enhancing AI image editing. This model maintains consistent details across multiple edits, unlike previous systems. Users can now transform subjects in uploaded photos while preserving original likenesses, even through successive modifications. This advancement in AI-powered image editing remembers details rather than creating random variations with each edit.

SMRTR provides this summary for quick context. The original article belongs to Ars Technica.

Read the original article
SMRTR AI

Get the next batch of curated summaries in your inbox.

This archive is built from SMRTR newsletter summaries. Subscribe for hand-picked stories without the extra noise.