> 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.
I had to leave out a ton of details in the training process. But at every step, codex/cc built me a dev tool to navigate the complexity. That was such a unique side project experience.
interesting with the alcatraz island - I notice its invented some houses, and turned a cruise ship into a rock. I appreciate the difficulty and getting a lora to understand it - despite this the finished project is beautiful
I also feel that some of the technical explanations are a little dense here in the dev blog. I forget who it was who I saw mentioning it here on HN, but I've been having a lot of success with getting models to (re)write technical explanations in https://en.wikipedia.org/wiki/Simplified_Technical_English
Honest opinion: Really charming on first look, but nothing where you can get lost in the details, because once you look closer, the soullessness of the generated imagery comes through. So I spent about 5 minutes looking at it, then moved on, and likely won't ever go back there.
With other things, like Floor796 that other people pointed out, I can spend so much time looking at all the labor of love that went in there, but making something to look at too closely likely wasn't the point here.
Ouch, this seems unnecessarily harsh for a side project made for fun. This might be acceptable if this was a low effort single prompt to an AI but it’s pretty clear from the write up that that is far from the case.
I was thinking the same..in fact it made me think enough that I wrote a blog/rant article about the topic AND created then a HN account. Well not this one specifically but all the other projects together I have seen recently and I just happened to have time today
https://burnoutdv.bearblog.dev/the-golden-age-of-hobbyiest-p...
You summarize it well. Are you on the Fediverse by any chance? If not, you might enjoy it you'll find lots of people there who still make art, write code and are interested in learning.
I haven't used it but Vexcel makes oblique imagery available. They use planes I believe to get multiple passes of each are they image and from various angles. Then they combine it and make the maps available.
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!
Nice! But for a city renowned for its steep streets, this looks suspiciously flat :) Ok, you could say it's only a 3D rendering of a 2D map, and it probably has to be this way for practical reasons, to avoid hills obscuring objects behind them, because you can't rotate the map as far as I can see, but not seeing actual height represented in a 3D view still takes some getting used to.
Also, there are neighbourhoods and landmarks, but not actual street names as far as I can see? Not to mention transit stops/lines and other fancy stuff one could add...
It’s vibe coded but it’s not slop. There’s a lot of human input here. So either the author overlooked the elevation issue or it was a deliberate decision, but in any case you can’t just pin this on “LLMs don’t understand isometric 3D”.
I've been busy with a rendered isometric map recently and I figured this is something Opus can help with, but it was near useless at understanding isometric designs along with elevation changes. It kept me busy for days.
This is incredibly beautiful.
A few months back I tried to build a my own version of Google Earth rendered in voxels. Basically building from the terrain heightmaps scans available in open public data. Making it smooth and tessellation to work was incredible amount of work even for a simple vexed renderer
https://codetiger.in/earth/
Nice, but not sure I agree with your use of voxels. It appears more like pixelated height map, not the use of 3d pixels. From what I see every position on the globe can only have a single elevation
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!
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.
I've spent about a month all told in SF over a couple visits.
As a devout midwesterner, I didn't think I was going to enjoy the place. Having spent a bit of time there however, and having been shown around by natives, I absolutely get it.
There's so much to see and do packed in a small area, and the air just feels electric.
I'm currently playing with something a bit similar and I was wondering about the fair use aspect.
What's the consensus on sharing the stylized assets created by diffusion models based on reference photos from e.g. Google Earth? Can the final output be shared as public domain or do Google, Airbus, et al. still hold some rights over them?
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.
Like the new york one, its just...unpolished. I dare to say slop. I am sure the author put some effort into it, BUT its just not there for me. The wiggly lines, the blurry designs and just everything. With something is pixelart or appears to be, I expected it to be pixel perfect, not just some random picture that looks like pixelart on the first glance.
The idea feels neat, but the execution needs so much more touch and polish. Maybe even handcrafting to be impressive.
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?
Behind the scenes stuff:
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.
> I'm stoked for the golden era of side-projects!
Love that attitude. Me too!
very inspired by you!
glad you liked it!
I had to leave out a ton of details in the training process. But at every step, codex/cc built me a dev tool to navigate the complexity. That was such a unique side project experience.
interesting with the alcatraz island - I notice its invented some houses, and turned a cruise ship into a rock. I appreciate the difficulty and getting a lora to understand it - despite this the finished project is beautiful
I also feel that some of the technical explanations are a little dense here in the dev blog. I forget who it was who I saw mentioning it here on HN, but I've been having a lot of success with getting models to (re)write technical explanations in https://en.wikipedia.org/wiki/Simplified_Technical_English
Really cool stuff
Honest opinion: Really charming on first look, but nothing where you can get lost in the details, because once you look closer, the soullessness of the generated imagery comes through. So I spent about 5 minutes looking at it, then moved on, and likely won't ever go back there. With other things, like Floor796 that other people pointed out, I can spend so much time looking at all the labor of love that went in there, but making something to look at too closely likely wasn't the point here.
For context, Floor796: https://floor796.com/
Note that clicking the characters shows extra information.
Protip, visit About -> FAQ; there are many interesting questions like “What interactive elements are there?”.
Previously discussed: https://news.ycombinator.com/item?id=46401612 (and others).
Wait, that's an example of something that's supposed to be better?
Ouch, this seems unnecessarily harsh for a side project made for fun. This might be acceptable if this was a low effort single prompt to an AI but it’s pretty clear from the write up that that is far from the case.
FWIW I thought this was really cool.
I don't think was unkind, and I think that if you make something public, opinions are always warranted.
For me it's the copy, it really does read as soulless slop and I think there are many people who are just tired of it.
I was thinking the same..in fact it made me think enough that I wrote a blog/rant article about the topic AND created then a HN account. Well not this one specifically but all the other projects together I have seen recently and I just happened to have time today https://burnoutdv.bearblog.dev/the-golden-age-of-hobbyiest-p...
> You are doing a hobby project, why do you fixate about results?
You're assuming his goals are the same or should be the same as yours.
IMO, it looks really cool, I'm sure it took lots of effort despite the AI coding help, and I thoroughly enjoyed looking at it and taking the tours.
Just because it's possible to create things like this doesn't devalue the work of true pixel artists.
You summarize it well. Are you on the Fediverse by any chance? If not, you might enjoy it you'll find lots of people there who still make art, write code and are interested in learning.
https://arstechnica.com/science/2018/04/these-oblique-satell...
"Satellite images from highly oblique angles are pretty mindblowing"
If u like this u will like that
woahhh, these are so beautiful!
I haven't used it but Vexcel makes oblique imagery available. They use planes I believe to get multiple passes of each are they image and from various angles. Then they combine it and make the maps available.
https://vexceldata.com/
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!
Men in Black: https://floor796.com/#b2r4,541,605
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.
Nice, love it!
i remember seein men in black here
Nice! But for a city renowned for its steep streets, this looks suspiciously flat :) Ok, you could say it's only a 3D rendering of a 2D map, and it probably has to be this way for practical reasons, to avoid hills obscuring objects behind them, because you can't rotate the map as far as I can see, but not seeing actual height represented in a 3D view still takes some getting used to.
Also, there are neighbourhoods and landmarks, but not actual street names as far as I can see? Not to mention transit stops/lines and other fancy stuff one could add...
It's vibe coded. LLM's have a hard time understanding elevation and isometric display.
It’s vibe coded but it’s not slop. There’s a lot of human input here. So either the author overlooked the elevation issue or it was a deliberate decision, but in any case you can’t just pin this on “LLMs don’t understand isometric 3D”.
I've been busy with a rendered isometric map recently and I figured this is something Opus can help with, but it was near useless at understanding isometric designs along with elevation changes. It kept me busy for days.
from his dev blog: "All map math happens in a single fixed ... plane... The intended effect was a classic Sim City view of the city. "
Sim City 2000 for example had elevation [1]. The issue is that LLM's simply don't "get this". It's vibecoded.
[1] https://patcoston.com/sc2k/city/images/Calebopolis_Big.png
This is incredibly beautiful. A few months back I tried to build a my own version of Google Earth rendered in voxels. Basically building from the terrain heightmaps scans available in open public data. Making it smooth and tessellation to work was incredible amount of work even for a simple vexed renderer https://codetiger.in/earth/
Nice, but not sure I agree with your use of voxels. It appears more like pixelated height map, not the use of 3d pixels. From what I see every position on the globe can only have a single elevation
Each pixel is a cube drawn at a certain height based on the terrain height map data. It’s not a volumetric render, I agree.
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!
ty!
This is really cool, it gives me SimCity 2000 vibes. I like that I can click on neighborhoods and regions and get more information about them!
Amazing, great project. The SV show music playing on opening was such a good detail to add, loved it!
Thank you for putting this together. Brought some fun memories back from my time living in SF
I'm reminded of the wonderful https://cannoneyed.com/projects/isometric-nyc project, also previously discussed here: https://news.ycombinator.com/item?id=46721802
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.
Would be extra awesome if there was a navigation app that used this map
Just one little thing: East of Buena Vista Park, you have a lake, it is actually the road which goes around the park.
Also, I would love to zoom in more. (pls give me the pixels)
Spurious lakes are an interesting issue I looked into a bit. 2 types of cases ended up becoming lakes: 1. "shadows" 2. flat green areas
I think a better data distribution should eliminate this. Also, my "water detector" was not too good and could be improved.
I wrote about a few of these things here: https://sf.isopolis.city/dev.html
more zoom enabled!
I've spent about a month all told in SF over a couple visits.
As a devout midwesterner, I didn't think I was going to enjoy the place. Having spent a bit of time there however, and having been shown around by natives, I absolutely get it.
There's so much to see and do packed in a small area, and the air just feels electric.
It's genuinely a different world.
This reminds me of my own project https://rainy-city.com
I'm currently playing with something a bit similar and I was wondering about the fair use aspect.
What's the consensus on sharing the stylized assets created by diffusion models based on reference photos from e.g. Google Earth? Can the final output be shared as public domain or do Google, Airbus, et al. still hold some rights over them?
The same "fair use" as when Google trained its model on everyone else's photos.
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.
I am not a fan of this.
Like the new york one, its just...unpolished. I dare to say slop. I am sure the author put some effort into it, BUT its just not there for me. The wiggly lines, the blurry designs and just everything. With something is pixelart or appears to be, I expected it to be pixel perfect, not just some random picture that looks like pixelart on the first glance.
The idea feels neat, but the execution needs so much more touch and polish. Maybe even handcrafting to be impressive.
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?
yeah, there are a ton of issues especially around water. I've documented a bunch of them here: https://sf.isopolis.city/dev.html
I tried out a few ideas, but i think better training data around water will help a LOT.
Super cool! Can you talk a bit about how you built it?
hey thanks! i wrote it all up here: https://sf.isopolis.city/dev.html
Amazing! I was sad I couldn't zoom in more tho
oooof, I can actually allow more zoom (was just embarrassed at bad pixels)
more zoom enabled!
Fantastic project! Sim-city over San Francisco.
THIS IS SICK! The BGM, the SFX, the visual are all perfect. My favorite is the banner plane, this is really really SF
haha ty!
It would be nice to have a Google or Apple maps version of this. I would also love to see this while driving.
Wow, very impressive! But where is the bulldozer tool? I have some landscaping to do.
Sorry but that is not pixel art.
Absolutely amazing Love to see how much we can go out of the box. Great work
I lived in San Francisco for 15 years, and love this. Great work!
>ghibli-style pixel-art
I suppose that explains the yellow filter and the mixels
Crazy to me that people engage with this. This is not pixelart or any art really, it's just a weird blurry mess. Looks terrible.
Reminds me "transport tycoon", very cool!
Unwanted sound! Not cool.
sorry! i debated this quite a bit, but the sv opening credits was too good to not include :(
No biggie, just almost woke up a household of sleeping people
Wow, nice prompting!
This is really cool!
time to push the boundaries of your creation
it's pretty interesting
Similar take by Levels.fyi: https://www.levels.fyi/atlas
that's pretty cool...
v cool!
well done! The opening music made me lol
A few AI anomalies, like several roads turning into rivers and lakes.
There are also a few massive square ponds in the Tenderloin that I am pretty sure do not exist lol
But I like the idea.
yeah, there are a ton of issues wrt water. I've documented a few of them here: https://sf.isopolis.city/dev.html
Planning to fix in the next version!
Needs a slight yellow filter over everything too.
Less #127614 more #73ba14
So it looks less like Illinois