I'm with the author on this one. I'm working on a Stable Diffusion based word guessing game (https://diffudle.com/). If you look at the prompts and the actual images, they are miles apart. This is after I reject multiple prompts and multiple images from the selected prompt. The worst part is Midjourney is able to create much better images from the same prompt.

At this point, I'm seriously considering renaming the product and just move with another image generator.