-2
I think everyone is overcomplicating how to get good AI image results
For months, I kept getting weird, melted faces in my AI art, even with detailed prompts. The common advice was to add more and more descriptive words. Last week, I tried the opposite: I used a very short, clear prompt like 'a portrait of a woman, smiling, sharp focus' and then used the negative prompt box to list what I didn't want, like 'blurry, deformed, extra fingers'. The next 10 images were all clean and usable. Has anyone else found that simpler prompts with strong negative instructions work better for them?
3 comments
Log in to join the discussion
Log In3 Comments
kim.dylan19d ago
Your point about negative prompts is spot on, but the short prompt part might be a bit misleading. It works for simple concepts like a portrait. For something more complex, like "a cyberpunk samurai repairing a robot in a neon alley," you still need those key details in the main prompt. The real trick is using the negative box to block the common glitches, which lets the main prompt focus on the creative idea instead of fixing errors.
5
nancy3011d ago
That's a really good point about complex scenes. So for something like the cyberpunk samurai, you'd still describe the alley and the neon lights in the main prompt. But what exactly do you put in the negative box for a scene that detailed? Just the usual 'deformed, blurry' stuff, or are there specific negative terms for, say, a robot's parts merging weirdly with the samurai's armor? Trying to figure out the strategy for more than just portraits.
1