Comment by spondylosaurus | Hacker News Reader

Comment by spondylosaurus | Hacker News Reader

This may not be the reason he's "losing" money here, but I was struck by how much less... impressive that piece is to me now compared to when I first saw it. (Visually impressive; I've always known it was from Midjourney.)

When the news first broke about it winning an award, I was like "well damn, I can see why—it's visually striking!" But the longer I look at it, and the more LLM-generated images I see in general, the less this one stands out to me. It's still pleasing, but seems less unique in both its strengths and flaws: the soft glowing lights, the tasteful muted palette, the random greebled details.

And it bothers me that the glowing orb/archway in the center has a distinct border around most of its circumference, but the part from 4 to 6 o'clock is fuzzier and blends into the nearby wall(?) :P

AI-generated images are interesting in that, in general, the more you look at them, and in particular the more you look at the detail, the worse they look. This is, arguably, one simple way to distinguish them from actual art.

>the part from 4 to 6 o'clock is fuzzier and blends into the nearby wall

Kind of like a Rembrandt or something.

I guess there's a reason it's always been said "there's no accounting for taste" :)

But only part of it blends! If the whole circumference was like that, it wouldn't bug me.

I know what you mean, there's something to bug everyone ;)

Maybe it's not going to be too easy to reach the level of a "masterpiece" with only a non-owner to bring it into the world?

Pretty images are worthless, there's no point staring at images that have were made without intention or effort. Making a prompt is hardly any effort and more of a lucky hit.

Making a good generated image is way more than typing a prompt.

How? Seriously, beyond coming up with the prompt, how is synthetic content more then typing a prompt

Look for ComfyUI tutorials on YouTube. Creating something unique is elaborate and requires developing skills no different than Photoshop or any other digital art tool.

There's equally no point staring at images that were made with intention or effort either.

It doesn't pass a blind scientific placebo test.

There are no "LLM-generated images". These images are generated using diffusion models. LLMs are very different from diffusion models.

https://en.m.wikipedia.org/wiki/Diffusion_model

Reply on news.ycombinator.com