Hacker News Reader

Comment by carrolldunham | Hacker News Reader

The title excited me - maybe someone succeeded making new art that looks like the old pre-renders, maybe a convincing imitation of the scanline render look. Instead it was a vapid article about tossing pixel art into img-2-img and getting some tenuously related junk.

View on HN

He didn't even do that. He used text descriptions; the original pixel art wasn't involved.

I guess that explains why the results were only vaguely related to the original pictures.

I think the new images look jarring next to the original 8-bit Konami style font at the bottom, the look clashes in my mind. I would have pixelated the generated images and dithered them down to a smaller palette to look more retro. Or kept the hi-res images but subtituted the fonts to something more detailed and modern.

But that's just me.

It reminds me of those HD texture packs for Minecraft in the early days that would attempt to map photorealistic textures onto a world almost entirely made of cubes. Yes it's more high-fidelity, but it adds nothing except emphasizing the low fidelity of everything else.

I agree with you. The other point it makes to me is that AI art generation doesn't turn non-artists into artists, no matter how many programmer types suddenly think they can replace artists now. You still need a developed sense of taste and style, which lets face it, outside of software, many programmers do not have.

Reply on news.ycombinator.com