Someone at a meetup said my AI art looked too much like everyone else's

I was showing my Midjourney stuff at a local tech meetup in Austin, and a guy told me my images felt generic. He said they were technically good but had no real point of view. So I started feeding it my own sketches and photos as a base instead of just text prompts. After about a month of this, my outputs got way more unique and less predictable. Has anyone else tried using their own work as a starting point for generative art?

3 comments

3 Comments

josephs2618d ago

That's basically how it works for everyone, though. The AI is trained on a huge dataset, so text prompts alone will always pull from that common pool.

spencer37718d ago

Hold up, @josephs26, that's not totally true. The training data is huge, but the way you write your prompt can steer it to really unique outputs. It's about giving super specific details and context the model has to weave together in a new way. If you just ask for a "dog," yeah, you'll get generic stuff, but describe a three-legged corgi wearing a tiny raincoat in a 1980s diner, and the result feels way more original.

webb.xena4d ago

Wait, a three-legged corgi? That's the part that got me. I've seen a lot of weird prompts, but picturing how it would even stand in a diner booth is just wild.