I’ve searched extensively but haven’t found a solution yet beyond using GPT-4 or GPT-4o.
Is there a way to use the API to upload images and create consistent characters from them?
I want to scale an idea I have, but so far, I can only generate the images with GPT-4 or GPT-4o.
I assumed the API would have this capability, but I haven’t figured it out yet.
Any help would be greatly appreciated! 