---
title: Gemini "Nano Banana" image editing capability
url: https://calvin.my/posts/gemini-nano-banana-image-editing-capability
published: 2025-09-08
updated: 2026-09-16
category: AI
tags:
- gemini
- Nano Banana
summary: The post evaluates Gemini Flash 2.5 Image, nicknamed Nano Banana, through edits to a generated portrait. It largely preserved the subject’s identity while successfully changing pose, adding a realistic shirt logo, and introducing a window whose light affected the character. A subtle lighting adjustment produced little visible change, possibly due to the prompt. Overall, repeated edits retained recognizable character consistency, suggesting broader practical uses for iterative image editing.
---

# Gemini "Nano Banana" image editing capability

This article tests the image editing capability of the new Gemini "Nano Banana" (aka Gemini Flash 2.5 Image) model.

* * *

## Our Tests

1. First, let's create a test subject using a different model (OpenAI GPT Image 1).

   ```markup
   [GPT Image 1]
   Create a half-body portrait of a young east asian lady, in her 20s.
   Straight, short brown hairs. Black eyes. Fair Skin.
   with a natural smile.
   ```

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/f7c66757-6c91-4ca8-ab19-79eb8c50af53.webp)

2. Let's make a small change. 

   ```markup
   [Nano Banana]
   wink with finger showing V sign
   ```

   - The character features are almost the same, though the hair color is slightly different, which is overall acceptable.
   - It is also observed that the wrinkles on the clothes near the character's left arm became more obvious. This is natural because now the character has raised her hand.

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/141828c3-0d5c-44fc-b509-9630ad3a7ac7.png)

3. Try to adjust the light source and shadow.

   ```markup
   [Nano Banana]
   move the light source to slightly lower than the current one
   ```

   - It seems like nothing changes except that the head angle moves slightly.
   - This could be due to bad instruction given.

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/cbf9605d-74b9-42bd-9f4a-27a2de9c161c.png)

4. Next, let's add something that does not exist in the original photo.

   ```markup
   [Nano Banana]
   print text logo calvin.my on the left side of the T-shirt. it must looks natural, a if it were part of the T-shirt deign. use cozy font.
   ```

   - The result is very decent. The logo looks like it is sewn onto the shirt and follows the texture of the cloth.

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/e26cd549-6248-4c7d-b161-ea48a5808d66.png)

5. Let's try to test the light source one more time, with more significant changes, e.g. adding a window.

   ```markup
   [Nano Banana]
   add a window at the left side in the background. A clear glass window, showing a noon with clear sky. please consider additional light source from the window on top of the existing indoor light source.
   ```

   - This is much better then the earlier test. We can see the left side of the character has been significantly impacted by the new light source.

   ![](https://camy-pub.s3.ap-southeast-1.amazonaws.com/8a096b97-6dc1-4b42-8be5-9e0a1d405bb6.png)

* * *

## Findings
Despite being processed multiple times, we can still recognise the same character from the original image. This seems to be a big improvement and opens up a lot of new use cases.