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.
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.