> The source is Google Photorealistic 3D Tiles. Isometric.nyc explored and rejected the use of 3d building data. It is pretty insane that US gov has free LIDAR data for every city in the US available to the public. I spent <30mins exploring this and stuck to google 3d images. Claude Code whipped up a scraper to stream the 3D Tiles and render with three.js. This gives the best "real" texture base for the model to learn from. Anything else would involve a LOT of manual work to get the inputs right.
> Now that we have the 3D tiles, we need to generate the ground truth pairs for training! Similar to isometric.nyc, I generated a few ghibli-style pixel-art images using Google's Nano Banana. SF terrain is very interesting. There are quite a few distinct features like skyscrapers in FiDi, the hills in the southeast, 2 iconic bridges, lots of coastline, piers, parks, suburban grids and lots of water. I generated a ton of images and curated from them. Getting consistent style was a challenge. There was a LOT of manual trial and error. But as usual, Claude Code added this feature to the dev app that allowed me to select the best images and approve them.
> If it feel like I am gushing over them, it is because I am. I'm stoked for the golden era of side-projects!
As soon as I see it was generated with Qwen I almost immediately write it off or lose interest in whatever 'work' you did put into it. Acknowledging that there is some work here, but other than that, no gushing. People saying this is impressive 'especially if you know how much work isometric maps are' etc.... what are you talking about? It's built from previous work and has none of the charm of knowing some hardcore pixel editing work was put into each tile or icon or whatever. It's.. nothing.
This could be a great anecdotal benchmark for agent/model progress. I wonder how much easier things have gotten with the latest Codex/Claude vs. when isometric.nyc was made.
Those who know game dev know making good isometric maps can be deceptively difficult. You grabbed that bull by the horns and did so beautifully. Well done!
Incredible. It's easy to just go on browsing and exploring. The massive, scrollable pixel art aspect reminds me a little of Floor796: https://floor796.com/
This is amazing, it got everything I could think of but not all, where’s little nightmares, silent hill, naruto, men in black, for a starter. But it’s neat regardless!
Very cool! Yesterday my wife and I watched Inside Out, and seeing the San Francisco setting felt very familiar (last year, 2025). Last year, in 2025, my wife and I went to San Francisco for our honeymoon. This website also showed me many familiar places.
Really cool. I can see some issues, like Starr King park turned into a lake for some reason, but it’s so much fun to look at. Do you have any way to patch errors and discontinuities at the tile boundaries?
https://sf.isopolis.city/dev.html
> The source is Google Photorealistic 3D Tiles. Isometric.nyc explored and rejected the use of 3d building data. It is pretty insane that US gov has free LIDAR data for every city in the US available to the public. I spent <30mins exploring this and stuck to google 3d images. Claude Code whipped up a scraper to stream the 3D Tiles and render with three.js. This gives the best "real" texture base for the model to learn from. Anything else would involve a LOT of manual work to get the inputs right.
> Now that we have the 3D tiles, we need to generate the ground truth pairs for training! Similar to isometric.nyc, I generated a few ghibli-style pixel-art images using Google's Nano Banana. SF terrain is very interesting. There are quite a few distinct features like skyscrapers in FiDi, the hills in the southeast, 2 iconic bridges, lots of coastline, piers, parks, suburban grids and lots of water. I generated a ton of images and curated from them. Getting consistent style was a challenge. There was a LOT of manual trial and error. But as usual, Claude Code added this feature to the dev app that allowed me to select the best images and approve them.
Love that attitude. Me too!
As soon as I see it was generated with Qwen I almost immediately write it off or lose interest in whatever 'work' you did put into it. Acknowledging that there is some work here, but other than that, no gushing. People saying this is impressive 'especially if you know how much work isometric maps are' etc.... what are you talking about? It's built from previous work and has none of the charm of knowing some hardcore pixel editing work was put into each tile or icon or whatever. It's.. nothing.
This could be a great anecdotal benchmark for agent/model progress. I wonder how much easier things have gotten with the latest Codex/Claude vs. when isometric.nyc was made.
Naruto: https://floor796.com/#t2l4,684,675
The author continues adding and refining the project, so if it isn't in there yet, perhaps in the future.