Image generation isn't what most devs spend most of their time on?

Interesting. Have been using Gemini, Gpt and Claude extensively in parallel and never noticed that.

It is semi-competent at making SVGs. Which are the only kind of images I really need in dev work.

For marketing or personal stuff I do sometimes want images, but I don't really mind going somewhere else for that

I'm switching over to Claude from OpenAI, and I don't care. OpenAI's image generation is terrible anyway. Just try to get it to generate something to scale, like a cabinet for a specific kitchen or bathroom space. Give it all the explicit constraints, initial sketches, etc. it wants.

The results are laughably bad.

Sure, it does get some of the tones and features, but any kind of actual real-world constraint is so far off, and the dimension indicators it includes are hilarious if they weren't so bad.