I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents.
I didn't write a single line of code.
Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped!
I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity:
Very impressive result! are you taking requests for the next ones? SF :D Tokyo :D Paris :D Milan :D Rome :D Sydney :D
Oh man...
I see you used Gemini-CLI some but no mention of Antigravity. Surprising for a Googler. Reasons?
I used antigravity a bit, but it still feels a bit wonky compared to Cursor. Since this was on my own time, I'm gonna use the stuff that feels best. Though, by the end of the project I wasn't touching an IDE at all.
Appreciate that writeup. Very detailed insights into the process. However those conclusions left me on the fence about whether I 'liked' the project. The conclusions about 'unlocking scale' and commodity content having zero value. Where does that leave you and this project? Does it really matter that much that the project couldn't exist without genAI? Maybe it shouldn't exist then at all. As with alot of the areas AI touches, the problem isn't the tools or use of them exactly, it's the scale. We're not ready for it. We're not ready for the scale of impact the tech touches in multitude of areas. Including the artistic world. The diminished value and loss of opportunities. We're not ready for the impacts of use by bad actors. The scale of output like this, as cool as it is, is out of balance with the loss of huge chunk of human activity and expression. Sigh.
At the risk of rehashing the same conversation over and over again, I think this is true of every technology ever.
Personally I'm extremely excited about all of the creative domains that this technology unlocks, and also extremely saddened/worried about all of the crafts it makes obsolete (or financially non-viable)...
Does it really matter that much that a sewage treatment plant couldn't exist without automated sensors? Maybe it shouldn't exist then at all.
I was most surprised by the fact that it only took 40 examples for a Qwen finetune to match the style and quality of (interactively tuned) Nano Banana. Certainly the end result does not look like the stock output of open-source image generation models.
I wonder if for almost any bulk inference / generation task, it will generally be dramatically cheaper to (use fancy expensive model to generate examples, perhaps interactively with refinements) -> (fine tune smaller open-source model) -> (run bulk task).
Edit: i see now, the error is due to the cloudflare worker being rate limited :/ i read the writeup though, pretty cool, especially the insight about tool -> lib -> application
Not working here either. Two different errors with two different browsers on Arch.
- Chromium: Failed to load tiles: Failed to fetch
- Zen: Failed to load tiles: NetworkError when attempting to fetch resource.
Same in Safari on macOS here, FWIW.
Author here: Just got out of some meetings at work and see that HN is kicking my cloudflare free plan's butt. Let me get Claude to fix it, hold tight!
So, wait: this is just based on taking the 40 best/most consistent Nano Banana outputs for a prompt to do pixel-art versions of isometric map tiles? That's all it takes to finetune Qwen to reliably generate tiles in exactly the same style?
Also, does someone have an intuition for how the "masking" process worked here to generate seamless tiles? I sort of grok it but not totally.
Failed to load tiles: NetworkError when attempting to fetch resource.
Seems to have been hugged to death as of now
Insane outcome. Really thoughtful post with insights across the board. Thanks for sharing
> This project is far from perfect, but without generative models, it couldn’t exist. There’s simply no way to do this much work on your own,
Hey HN!
I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents.
I didn't write a single line of code.
Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped!
I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity:
http://cannoneyed.com/projects/isometric-nyc
Very impressive result! are you taking requests for the next ones? SF :D Tokyo :D Paris :D Milan :D Rome :D Sydney :D
Oh man...
I see you used Gemini-CLI some but no mention of Antigravity. Surprising for a Googler. Reasons?
I used antigravity a bit, but it still feels a bit wonky compared to Cursor. Since this was on my own time, I'm gonna use the stuff that feels best. Though, by the end of the project I wasn't touching an IDE at all.
Appreciate that writeup. Very detailed insights into the process. However those conclusions left me on the fence about whether I 'liked' the project. The conclusions about 'unlocking scale' and commodity content having zero value. Where does that leave you and this project? Does it really matter that much that the project couldn't exist without genAI? Maybe it shouldn't exist then at all. As with alot of the areas AI touches, the problem isn't the tools or use of them exactly, it's the scale. We're not ready for it. We're not ready for the scale of impact the tech touches in multitude of areas. Including the artistic world. The diminished value and loss of opportunities. We're not ready for the impacts of use by bad actors. The scale of output like this, as cool as it is, is out of balance with the loss of huge chunk of human activity and expression. Sigh.
At the risk of rehashing the same conversation over and over again, I think this is true of every technology ever.
Personally I'm extremely excited about all of the creative domains that this technology unlocks, and also extremely saddened/worried about all of the crafts it makes obsolete (or financially non-viable)...
Does it really matter that much that a sewage treatment plant couldn't exist without automated sensors? Maybe it shouldn't exist then at all.
I was most surprised by the fact that it only took 40 examples for a Qwen finetune to match the style and quality of (interactively tuned) Nano Banana. Certainly the end result does not look like the stock output of open-source image generation models.
I wonder if for almost any bulk inference / generation task, it will generally be dramatically cheaper to (use fancy expensive model to generate examples, perhaps interactively with refinements) -> (fine tune smaller open-source model) -> (run bulk task).
Not working here, some CORS issue.
Firefox, Ubuntu latest.
Cross-Origin Request Blocked: The Same Origin Policy disallows reading the remote resource at https://isometric-nyc-tiles.cannoneyed.com/dzi/tiles_metadat.... (Reason: CORS header ‘Access-Control-Allow-Origin’ missing). Status code: 429.
Edit: i see now, the error is due to the cloudflare worker being rate limited :/ i read the writeup though, pretty cool, especially the insight about tool -> lib -> application
Not working here either. Two different errors with two different browsers on Arch.
- Chromium: Failed to load tiles: Failed to fetch
- Zen: Failed to load tiles: NetworkError when attempting to fetch resource.
Same in Safari on macOS here, FWIW.
Author here: Just got out of some meetings at work and see that HN is kicking my cloudflare free plan's butt. Let me get Claude to fix it, hold tight!
So, wait: this is just based on taking the 40 best/most consistent Nano Banana outputs for a prompt to do pixel-art versions of isometric map tiles? That's all it takes to finetune Qwen to reliably generate tiles in exactly the same style?
Also, does someone have an intuition for how the "masking" process worked here to generate seamless tiles? I sort of grok it but not totally.
Failed to load tiles: NetworkError when attempting to fetch resource.
Seems to have been hugged to death as of now
Insane outcome. Really thoughtful post with insights across the board. Thanks for sharing
> This project is far from perfect, but without generative models, it couldn’t exist. There’s simply no way to do this much work on your own,
Maybe, though a guy did physically carve/sculpt the majority of NYC: https://mymodernmet.com/miniature-model-new-york-minninycity...
Huh, the linked instagram account is no longer available :/
I still see it at https://www.instagram.com/minninycity04, with two video posts
TikTok content is still up https://www.tiktok.com/@balsastyrofoam300
I got a recommended video in Youtube just the other day, where a bunch of users made NYC in Minecraft at a 1:1 scale: https://www.youtube.com/watch?v=ZouSJWXFBPk
Granted, it was a team effort, but that's a lot more laborious than a pixel-art view.
Related:
New York City is being recreated at 1:1 scale inside Minecraft
https://news.ycombinator.com/item?id=46665589
Some people reported 429 - otherwise known as HN hug of death.
You probably need to adjust how caching is handled with this.
Hugged to death? :(
Seems so. Shame! Really wanted to see this.
You really, really do. It's quite something.
> Slop vs. Art
> If you can push a button and get content, then that content is a commodity. Its value is next to zero.
> Counterintuitively, that’s my biggest reason to be optimistic about AI and creativity. When hard parts become easy, the differentiator becomes love.
Love that. I've been struggling to succinctly put that feeling into words, bravo.
Really nice.
beautiful!
[dead]