alt Hacker NewsShow HN: Isometric SF – A pixel-art map of the SF Bay Area
Technical Write-up: https://www.justinchavez.com/blog/isometric-sf-how/
Hi HN! Showcasing this fun project. I took 1300 square miles of the SF Bay Area from Google Photorealistic 3D Tiles and transformed them into a cohesive pixel map. It's really fun to explore and stumble upon various famous landmarks like Apple Park, Palace of Fine Arts, or UC Berkeley.
The technicals involve using Nano Banana 2 to train a Qwen-Image-Edit 2511 LoRA which is used to prototype the style and generation methods. For final map I used Qwen to train a Klein 4B LoRA which reproduced the style at 1/4 of the cost. More details in the blog post.
Let me know what you think! I really enjoyed this process of fine-tuning smaller open source models.
If I did the map with Nano Banana 2 it would have cost around 7k USD!
Credit for the idea goes to Isometric NYC.
Comments
OP didn't mention it (or maybe I missed it), but the underlying imagery comes from the Google 3D photorealistic tiles API: https://developers.google.com/maps/documentation/tile/3d-til...
They offer a generous 1000 API calls per month for free, in case anyone is interested in replicating this.
This is neat but maybe we could call it "pixel-art-styled?" Pixel art is all about attention to detail; this is more like applying a shader (though I see some AI artifacts in there too.)
Here's a 7388 x 5097 photo I took from a friend's Cessna of the Mission from a similar angle in 2018 which provides a nice point of reference for comparing the fine details:
https://i.dllu.net/2018-04-14-23-31-28_DSC04018_6201e8e3a215...
You can see some buildings, like 350 Treat Ave, which is a white warehouse in the middle of the photo, are blended from two colors in this isometric viewer. It's yellow on the left and grey on the right, when in fact it is uniformly white throughout. This is probably due to image generation running separately on two tiles and then blending them together.
Still, from a distance, this looks great.
lat/lng mapping would be great
This is so beautiful! Something soothing and ultra clean about it. Maybe all the maps should have this rendered version as default.
Also see isometric Toronto: https://iso.sloptoronto.ca/#v=3&x=102672&y=64255&z=0.262
I thought I already saw that project few months ago, but turns out it's a similar submission under the same concept: "Isopolis – Isometric pixel map of SF "!
Looks great, I love the style you chose, it was enjoyable to move around and explore
I've done something similar with generating pixel-style images of Stockholm. Unfortunately imagegen models are quite bad at localised details. It looks good on the surface, but when you look closer or zoom in you see structurally things that don't make sense, like windows disappearing, or walls just not making any sense at all.
This misses large parts of the Bay Area, which is nine counties: Alameda, Contra Costa, Marin, Napa, San Mateo, Santa Clara, Solano, Sonoma, and San Francisco. Here, pretty much everything east of 680 and north of the Richmond Bridge is missing. No Mt. Diablo, no Livermore, only bits of Dublin, Pleasanton, San Ramon etc.
this is really cool, but I wish it was oriented north south (maybe thats not as pleasing re the isometry?), just because that's how I think about the city and navigating it, so this makes me like, instinctually rotate my head.
How much it cost you paint per km2 after training the model? I did (and publish here) https://www.tinyvalencia.com and got to 0.4$ per km2 after training the model (for 15$ or so).
Hi Justin, great writeup!
I really appreciate your human-written documentation because it's nice to read your thought process instead of LLM marketing soundbites.
re: orientation. I know it's creator's choice, but for me, it's either north or west towards the ocean. East makes me want to hold shift to rotate. :)
Thanks for making and sharing this!
I've been seeing a lot of these kinds of projects make the rounds on Twitter lately. Yours is just as good as the best of them, so great job making it more efficient without loss of quality!
But... I'm always disappointed when I zoom in and see that it's not actually pixel art, and it's full of the kinds of artifacts that are typical of any AI-generated imagery :(
It's always heartening to see stuff like this because it really throws into stark illumination just how much AI just can't make up for a lack of taste.
Wow, it captured the pool in my apartment complex. I love this! I was a bit disoriented by north being left.
Found my house in East Bay and it looks accurate, cool.
Is there any way to rotate the perspective, as in Google Maps with 2-finger gestures (touchscreens) or shift-drags (mice/etc)?
(I couldn't find it, if it already exists.)
This is my favorite one yet! I used to live in SoMa and this captured my apartment and the nearby Caltrain wonderfully!
This style seems achievable while retaining 3D rendering if the tiles are preprocessed in 3D instead of 2D and some clever shaders are used.
Awesome. Next step: Make the trains and cars move!
This is amazing and is 1:1 global map. Did you use google maps API to build this or UE5?
Just wanted to say... this is beautiful!
Grossly inaccurate due to lack of pixelized piles of human feces.
Looks great!
Impressive! And the aesthetics look great!
Can't seem to find Computer History Museum
Anyone able to?
Not bad. I feel like instead of using an image-mode model, it would be better to use a code model that generates the scene. Reason I think this is that the image generators aren't respecting the rules of "pixel art". Straight lines and flat planes are straight and flat in pixel art. These images are wavy and irregular.
Not pixel art. Downvoted
Sorry to be a downer, but this looks really bad to me. It completely lacks the sumptuous precision of real pixel art.