TIL an old trick for getting better AI image results when you're stuck
Honestly, I was trying to generate a picture of a mechanic's workshop for a flyer last month and the AI kept giving me these weird, clean, empty garages. I got frustrated and typed 'messy garage, tools on a bench, a half-finished coffee in a stained mug, afternoon light through a dirty window' instead of just 'workshop'. The difference was huge, it actually looked real. I guess the trick is to describe the scene like you're telling a story, not just naming the thing. Has anyone else found a specific way to phrase things that just clicks with these image generators?
So you're telling me the secret to good AI art is basically reverse psychology? Instead of "pretty sunset" we have to say "sunset with a weird cloud that looks like a fish and one power line in the corner." It's like trying to explain a messy room to a super tidy person, you have to point out the sock on the floor and the cup on the desk to make it feel lived in.
Yeah, that "describe the scene like you're telling a story" bit is the whole key. I found the same thing trying to get a picture of a forest path. Just saying "forest" gives you a generic stock photo. But saying "dappled sunlight on a muddy trail, roots sticking out, a broken branch on the ground" makes it feel like a real place. It's like you have to trick the AI into seeing the imperfect details.