Tested ChatGPT Images 2.0 this weekend. Here's what I learned.

First attempts: boring. Generic AI illustrations, nothing close to the examples on OpenAI's website.

Then I rewrote (well, Claude rewrote) the prompts with proper detail.
Specific composition.
Specific lighting.
Specific layout.
Specific text rendered verbatim.
The results changed.

So, the model is good, but I wouldn't say perfect. Character consistency is still not there. But text creation is indeed really good.

1 / 8

Lembit Loo Good insights, thank you for sharing! Yes, tested it, quite good results... at the same time bit of yet another incremental image generation tool upgrade. I might look at it differently if I were in photography/marketing functions, interested to hear the feedback from that side.
Apr 26 1 like

Kai Raun Thank you Gerlyn Tiigemäe! Good insights and tips! Have tested myself as well - design consistency has been a problem indeed, otherwise quite good results. Apr 26 1 like

Public author posts