Random examples:

1) I have a tricep tendon injury and ChatGPT wants me to check my tricep reflex. I have no idea where on the elbow you're supposed to tap to trigger the reflex.

2) I'm measuring my body fat using skin fold calipers. Show me were the measurement sites are.

3) I'm going hiking. Remind me how to identify poison ivy and dangerous snakes.

4) What would I look like with a buzz cut?

You should never rely on AI to do 1, 2 or 3, especially a sloppy model like this.

First three are interesting - all question / knowledge based where the answer is a picture. Hadn't really considered this.

The answer is a picture that almost certainly already exists.

Why would you want a program that just makes one up instead?

So you can feel 1000x better about yourself when 1000x more resources are used to create an extra special image just for you. Rather than the canonical one served from the Wikipedia (or Google image search) cache.

My most regular use-case is generating silly memes in group chats. If someone posts something meme-worthy or I come up with a creative response, image generation is good for one-off throwaway memes. A recent example was an "official license to opine on sociology", following someone arguing about credentialism.

Recently I also started using image generation models to explore ideas for what changes to make in my paintings. Although generally I don't like the suggestions it makes, sometimes it provides me with creative ideas of techniques that are worth experimenting with.

One way to approach thinking about it is that it's good for exploring permutations in an idea-space.

Mostly highly specific images in blog posts but I also use it for occasional comics.

https://mordenstar.com/portfolio/gorgonzo

https://mordenstar.com/portfolio/brawny-tortillas

https://mordenstar.com/portfolio/ms-frizzle-lava

I'm kind of reading between the lines, but sounds like "for fun" which makes sense / what I generally expected for why people use it

I think that's a fair assessment. I write a lot of bizarre fiction in my spare time, so Text2Image tools are a fun way to see my visions visualized.

Like this one:

A piano where the keyboard is wrapped in a circular interface surrounding a drummer's stool connected to a motor that spins the seat, with a foot-operated pedal to control rotation speed for endless glissandos.

Nano Banana is more of an image editing model, which probably has more broad use cases for non-generative applications: interior decorating, architecture, picking wardrobes, etc.

Definitely, but don't sleep on its generative capacities either. You can give it a image and instruct it "Use the attached image purely as a stylistic reference" and then proceed to use it as a regular generative model.

Indeed. Is Nano Banana now Google flagship image gen model (over Imagen 4)?

In my tests it does outscore Imagen3 and Imagen4 even in the generative capacity, but my benchmark is more focused around prompt adherence. I'd wager that for certain photorealistic tests Imagen4 is probably better.

https://genai-showdown.specr.net/?models=i3,i4,nb

Yeah... For some reason none of these are use cases in my day to day life. That said, I also don't open Photoshop very often. And maybe that's what this is meant to replace.

Not for everyone everyday, but a good tool to have in the toolbox. I recently was very easily able to mock up what a certain Christmas decoration would look like on the house. By next year, I'm sure that feature will be part of the product page.

I'm creating a team T-shirt from a bunch of kids drawings. The model has synthesize a bunch of disparate drawings into a cohesive concept, incorporate the team's name in the appropriate color and font, and make it simple enough for a T-shirt.

porn is probably the a biggest one?

but concept art, try-it-on for clothes or paint, stock art, etc

Nonconsenual pornography is the killer app.