Collection of GPT-image-generator 2.0 issues, bugs, and work-around tips (check first post)

I don’t understand what some of these posts are getting at. The issue is pretty easy to recreate and doesn’t go away with specific kinds of prompts. If i want a fantasy painting of a landscape or village or whatever, it will look good with the first few results in a chat. But after that, different requests get increasingly more messy unless you direct it to photorealistic generations (and then only works on more mundane objects and nothing too fantastical). Using references also causes weird artifacting in many gens, like we see. BoyuanChen0 on twitter says they’re working on it and will announce when they have it fixed. That suggests to me that this is a bug and unintended behavior. With Dalle-3 i could keep generating in the same chat with consistent quality. I don’t like that I can’t do that with image 2, that’s what i want fixed.