<div class="statcounter"><a title="Web Analytics" href="https://statcounter.com/" target="_blank"><img class="statcounter" src="https://c.statcounter.com/12795394/0/d64e9537/1/" alt="Web Analytics" referrerPolicy="no-referrer-when-downgrade">

Let's Try Out Nano Banana And See If It Is Really That Good

AI Quick Tips

In case you haven’t heard about it yet, Google recently released a new image model.  It is called Gemini 2.5 Flash Image (technically it is gemini-2.5-flash-image-preview).  They call it a State-of-the art image generation and editing model.  I believe them…

The code name for this model, that seems to have caught on, is Nano Banana.

Now you are caught up.


In normal Google-style, they didn’t have a huge announcement.  They just made the model available.  People found it and are going crazy about it.  Why?  Well, I can’t speak for “people”, but my guess is because it actually works.  


This has been Google’s pattern throughout these AI races.  Let the other companies have these massive over-promises and faceplants.  Or wait for the competition to release models with some kind of pricing structure and then Google releases their version (which happens to be better) silently and for free.  


I had already played around with nano banana in Google AI Studio a little bit.  Now it’s in Gemini.  Seems like a good enough reason to play around some more.


I started with these two images - A photograph of a single figurine standing in a patch of green grass with fallen brown leaves. The female figure has brown hair and is wearing a blue shirt and gray vest while holding a black camera. She is standing inside a glittery, orange half-sphere. The background is a blurry mix of dark green and brown.

A different Google AI-generated image of Danielle as a collectible toy.


And  A highly-detailed digital illustration of a small, round, furry monster with glowing blue eyes, sharp teeth, and two horns. Its fur is a mix of bright orange and turquoise blue with specks of glitter. The monster is standing on a dark, glistening ground, and in the background, a lightning bolt flashes in a cloudy orange and purple sky.

The infamous glitter monster (inside joke) - also AI-generated from a different model


Nano banana’s first task was to add the glitter monster to the other image. 

 

Here's the prompt I used -

(I attached both images to the prompt)

Reference the attached images

Add a glitter monster (subject of the second image) to the first image in a similar style


 

This is what it gave me -

 A photograph of two figurines in a patch of green grass with fallen brown leaves. On the left, a small, furry blue and orange monster figure with a grumpy expression and horns stands on its own. On the right, a girl figure with brown hair and a gray vest holds a black camera, standing inside an orange half-sphere filled with glitter. The background is a blurry mix of dark green and brown.

My take - good and bad.  The lines around the glitter monster are surprisingly clean.  That would have taken a while to do manually.  It’s not really in the same style though.


Let’s keep going.


Next prompt -

Make the glitter monster smaller and place it behind her inside of the orange ball


Result - 

 A photograph of two figurines standing in a patch of green grass with fallen brown leaves. On the right, a girl figure with brown hair and a green vest holds a black camera. Next to her, a small, furry blue and orange monster figure with a grumpy expression stands in a glitter-filled, orange half-sphere. The background is a blurry mix of dark green and brown.


A lot of good things happened here -

  • It is smaller
  • It is inside of ball
  • It is behind her
  • The halo around it is gone (not part of the prompt but it is consistent with the lighting inside of the ball)
  • It is clearly the same glitter monster that we started with (other image models have been known to change the image)

Why stop here.  Next prompt -


Change the color of the vest worn by the subject holding the camera to green

 A photograph of two figurines standing in a patch of green grass with fallen brown leaves. On the right, a girl figure with brown hair and a green vest holds a black camera. Next to her, a small, furry blue and orange monster figure with a grumpy expression stands in a glitter-filled, orange half-sphere. The background is a blurry mix of dark green and brown.


Nice!  The vest is changed (I didn’t specify what kind of green so what it chose is acceptable) and the rest of the image is unchanged.


Let’s go one more time.   Prompt -

Sprinkle some glitter on the floor of the orange ball by their feet

A photograph of two figurines standing in a patch of green grass with fallen brown leaves. On the right, a girl figure with brown hair and a green vest holds a black camera. Next to her, a small, furry blue and orange monster figure with a grumpy expression stands in a glitter-filled, orange half-sphere. The background is a blurry mix of dark green and brown.


Hmmmm.  It’s definitely more than just at their feet but c’mon! It’s a glitter monster.  It can’t be expected to only have a tiny amount of glitter so I accept this.


Verdict -  I think this is damn impressive.  One thing that I didn’t mention is that each of the image generations took about 5 seconds.  This is way faster than most other models (that don’t give you what you asked for…)  The edits weren’t perfect but the prompts were also (intentionally) simple.  I am confident that with better initial prompts or descriptive follow-up prompts, the model would give me whatever I asked for.


This is approaching game-changer level.  Not just on the image generation side - which isn’t showcased here but I’ve tried it and it is at least as impressive - but if it can edit this quickly and accurately, photographers and editors may need to step up their games.  And, to be clear, we still have a photography business as well so we are in that group.  


My advice - if you also have some kind of photo creation and/or editing component to your job or business, learn to use and master this tool today.  If it does replace the tool(s) that you currently use, you’ll still be able to keep pace with the times.  You can be mad about it later…


Well done Google.  These are crazy times…

Cartoon illustration of a smiling robot and a person standing together with floating keyboard shortcut keys (Ctrl, Shift, C, V, O, and Esc) around them on a starry blue background.

Save Time, Skip the Mouse

ChatGPT can do more than chat, it can save your wrists and your sanity. Our ChatGPT for Complete Beginners course is full of shortcuts (literal and figurative), and our blog tips are like bonus time-savers you didn’t know you needed.

Comments