OpenAI is so lagging behind in terms of image generation it is comical at this point.
They dropped a new image model last week using 4o to contextualize the request, it’s very very good. However it’s for paid subscribers only right now I believe.
However as you mentioned Stable diffusion and mid journey probably still have more customizability.
theterrasque@infosec.pub 1 year ago
You’re the one lagging behind. OpenAI’s new image model is on a different level, way ahead of the competition
YarHarSuperstar@lemmy.world 1 year ago
How so?
theterrasque@infosec.pub 1 year ago
It understands what you’re telling it, and can generate images from vague descriptions, combine things from different images just by telling it, modify it and understand the context - like knowing that “me” is the person in the image, for example.
mad_djinn@lemmy.world 1 year ago
you know enough about the model for me to immediately distrust your opinion on the matter. why don’t you head back to ycombinator or whatever hole you crawled out of
Ilixtze@lemm.ee 1 year ago
It is really sad that the most advanced model can only aspire to make derivative shit for techbro loosers,
YarHarSuperstar@lemmy.world 1 year ago
Okay so how does that compare to whatever competition you’re referencing