I tried this prompt:
Infographic explaining how the Datasette open source project works
Here's the result: https://simonwillison.net/2025/Nov/20/nano-banana-pro/#creat...I tried this prompt:
Infographic explaining how the Datasette open source project works
Here's the result: https://simonwillison.net/2025/Nov/20/nano-banana-pro/#creat...That said, I wonder if text is only good in small chunks (less than a sentence) or if it can properly render full sentences.
https://gemini.google.com/share/c9af8de05628
I did manage to get one image of a piano keyboard where the black keys were correct, but not consistently.
Even generating a standard piano with 7 full octaves that are consistent is pretty hard. If you ask it to invert the colors of the naturals and sharps/flats you'll completely break them.
"An infographic explaining how player.html works (from the player.html project on Github). https://github.com/pseudosavant/player.html"
And then it made one formatted for social: "Change it to be an infographic formatted to fit on Instagram as a 1:1 square image."
My experience is that ChatGPT is very good at iterating on text (prose, code) but fairly bad at iterating on images. It struggles to integrate small changes, choosing instead to start over from scratch, with wildly different results. Thinking especially here of architectural stuff, where it does a great job laying out furniture in a room, but when I ask it to keep everything the same but change the colour of one piece, it goes completely off the rails.
I've used Claude to generate fairly simple icons and launch images for an iOS game and I make sure to have it start with SVG files since those can be defined as code first. This way it's easier to iterate on specific elements of the image (certain shapes need to be moved to a different position, color needs to be changed, text needs an update, etc.).
FWIW not sure how Nano Banana Pro works though.
I've tried iterating on slides with test on them a bit and it seems to be competent at that too.
And that point you can either start over or just feather/mask with the original in any Photoshop type application.
But boy was it beautiful.
> “Data Ingestion (Read-Only)” is a bit off.
I’ve found in general that the first generation may not be accurate but a few rolls of the dice and you should have enough to pick a style and format that works, which you can iterate on.