Nano banana, identified as Gemini 2.5 Flash Image from Google DeepMind, is being rolled out to the Gemini app after rising to the top of the LMArena leaderboard. The model provides AI image editing that uses prompts instead of manual Photoshop work and excels at maintaining visual consistency. Unlike many generative systems that introduce unpredictable changes, nano banana can remember and preserve fine details across edits. Users can upload a photo and alter style or attire—such as reimagining someone as a matador or a '90s sitcom character—while keeping the result recognizable as the original subject.
Google first provided editing capabilities in Gemini earlier this year, and the model was more than competent out of the gate. But like all generative systems, the non-deterministic nature meant that elements of the image would often change in unpredictable ways. Google says nano banana (technically Gemini 2.5 Flash Image) has unrivaled consistency across edits-it can actually remember the details instead of rolling the dice every time you make a change.
This unlocks several interesting uses for AI image editing. Google suggests uploading a photo of a person and changing their style or attire. For example, you can reimagine someone as a matador or a '90s sitcom character. Because the nano banana model can maintain consistency through edits, the results should still look like the person in the original source image.
Collection
[
|
...
]