As NYC wakes up to the largest blizzard in years, I’d like to share [isometric.nyc/snow](http://isometric.nyc/snow) - a wintry mix of the original isometric pixel map of NYC .

This work builds on the original isometric.nyc ideas but aims to increasingly automate the process of generating the tiled images. I’ve written up a follow-up addendum at [cannoneyed.com/projects/isometric-nyc\#snow](http://cannoneyed.com/projects/isometric-nyc#snow) that describes some of this work, but the tl;dr is:

* ensuring that training data and generations are color balanced / normalized goes a long way for consistency (duh) * augmenting water with a crosshatch pattern allowed the model to learn what it was instead of hallucinating (interesting!) * dramatically increasing inference throughput on [modal.com](http://modal.com) meant I could generate 10s of thousands of tiles in a few hours at very little cost, allowing me to experiment much more rapidly

This project continues to be a lot of fun, but I’m now mostly focusing on the agentic workflows that power this kind of ambitious generation at scale. Can’t wait to share more soon.

Comments URL: https://news.ycombinator.com/item?id=47124712

Points: 10

# Comments: 2

I agree that "push button get image" AI generation is at best a bit cheap, at worst deeply boring. Art is resistance in a medium - but at what point is that resistance just masochism?

George Perec took this idea to the max when he wrote an entire novel without the letter "E" - in French! And then someone had the audacity to translate it to English (e excluded)! Would I ever want to do that? Hell no, but I'm very glad to live in a world where someone else is crazy enough to.

I've spent my 10,000 hours making "real" art and don't really feel the need to justify myself - but to all of the young people out there who are afraid to play with something new because some grumps on hacker news might get upset:

It doesn't matter what you make or how you make it. What matters is why you make it and what you have to say.

At some point I couldn't fiddle with the style / pipeline anymore and just had to roll with "looks ok to me" - the whole point of the project wasn't to faithfully adhere to a style but to push the limits of new technology and learn a lot along the way

But I didn't want to call it a "SimCity" map, though that's really the vibe/inspiration I wanted to capture, because that implies a lot of other things, so I used the term "pixel art" even though I figured it might get a lot of (valid) pushback...

In general, labels and genres are really hard - "techno" to a deep head in Berlin is very different than "techno" to my cousins. This issue has always been fraught, because context and meaning and technique are all tangled up in these labels which are so important to some but so easily ignored by others. And those questions are even harder in the age of AI where the machine just gobbles up everything.

But regardless, it was a fun project! And to me at least it's better to just make cool ambitious things in good faith and understand that art by definition is meaningful and therefore makes people feel things from love to anger to disgust to fascination.

But I didn't want to call it a "SimCity" map, though that's really the vibe/inspiration I wanted to capture, because that implies other things, so I used the term "pixel art" even though I knew it'd get a lot of (valid) pushback...

As with all things art, labels are really difficult and the context / meaning / technique is at once completely tied to genre but also completely irrelevant. Think about the label "techno" - the label is deeply meaningful and subtle to some and almost meaningless to others

- the way they represent image tokens isn't conducive to this kind of task

- text-to-image space is actually quite finicky, it's basically impossible to describe to the model what trees ought to look like and have them "get it"

- there's no reliable way to few-shot prompt these models for image tasks yet (!!)

I actually have a nice little water shader that renders waves on the water tiles via a "depth mask", but my fine-tunes for generating the shader mask weren't reliable enough and I'd spent far too much time on the project to justify going deeper. Maybe I'll try again when the next generation of smarter, cheaper models get released.

The issue is that the overall style was not consistent from tile to tile, so you'd see some drift, particularly in the color - and you can see it in quite a few places on the map because of this.