LoRA Trained on SFMTA CAD Drawings to Aerial Images
Hey I'm Kieran and I've been playing with the intersection (pun intended) of generative AI and civil engineering for roadways. I did a test run training a LoRA on the new Flux 2 Dev model using Fal's trainer useing a custom dataset of paired images from publicly available striping CAD drawings of street layouts to aerial images of the same area. The use case here is to allow urban planners to instantly visualize their proposed changes as they work with their existing tooling. This was just a quick experiment with a small data size that exceeded my expectations so I wanted to share with you…
What it does
In the maker’s words, at launch
Hey I'm Kieran and I've been playing with the intersection (pun intended) of generative AI and civil engineering for roadways. I did a test run training a LoRA on the new Flux 2 Dev model using Fal's trainer useing a custom dataset of paired images from publicly available striping CAD drawings of street layouts to aerial images of the same area. The use case here is to allow urban planners to instantly visualize their proposed changes as they work with their existing tooling. This was just a quick experiment with a small data size that exceeded my expectations so I wanted to share with you all. Watch a demo with instructions on how to test it out: https://www.youtube.com/watch?v=zS8pGoOfe00 Try it now (includes free credits) https://3dstreet.app/generator If you're really excited about running on your own hardware here are the lora weights: https://v3b.fal.media/files/b/0a87f41f/glySGbKtv8lzigPWzQDjb... I can writeup a longer blog post if interested in the details. This was only trained on 12 image pairs with text descriptions but it still cost about $100 on Fal. I'd love to do a larger run, but it does take a while to prepare all of the data and I'm hesitant to drop $2k. I'd be curious for the experts out there if you think the quality will increase if I use a larger sample size.
Does the same job
all alternatives →- WBWe built a powerful and free AI research assistant2024 · join.modularmind.app · ▲7
Hi everyone, We have been developing a platform to enable professionals to build AI assistants to help them through their work. After a few months, we realized people are trying to sell basic functionalities that can be built from scratch in a couple of hours. Due to this, individuals who are not familiar with the current SOTA are misinformed about the potential of generative models. So, we decided to open up some of our most popular templates as standalone tools for free to empower individuals and set a solid standard for what people should expect. We believe the barrier to accessing…
- IBI built an open-source AI system for drones2023 · github.com · ▲5
Hey HN! I just released a suite of AI models for deployment on UAV and other "overhead" devices to provide some understanding of the world below. The objective is to empower all sorts of open-source use cases around search and rescue, wildfire prevention, ground risk mitigation for flight over populated areas etc... The neural networks are trained for a bunch of different devices from big GPUs to tiny edge AI cameras like the Luxonis OAK, with some optimised ones for Nvidia TensorRT and other cool bits and pieces too. The main release package also includes some boilerplate code for running…
- TNThe No-Code Tool I built for my own AI Experiments2024 · github.com · ▲5
Hi guys, I’m excited to share an update on ReproModel, an open-source toolbox designed to streamline the testing and reproduction of machine learning models. I, like many of you, have really struggled with benchmarking and comparing models, from missing code, to opaque experiment parameters slowing the process. I decided to take matters into my own hands, and created a mini-toolbox in my free time to streamline the process. The goal is to reduce the time and effort spent on replicating experiments, enabling researchers to focus on innovation rather than setup. Knowing this task is not an…
- AIAn interactive transformer “debugger” been working on in my free time2023 · github.com · ▲8
My focus has been shifting towards the ML alignment space recently, and in particular the ability to translate large transformer models into human understandable circuits and algorithms. This problem potentially isn't solvable, but it is one that some groups have had success with after large amounts of effort. In attempting to address this issue, I've been developing Transpector. A tool scaling up and reducing the barrier to entry of techniques that these teams have been showing success with. Techniques aiming to understand the internal mechanics of the model. Currently this tool is focused…
- WBWe built an AI Website builder with better output2024 · dorik.com · ▲8
Hey HN, After GPT-3 created waves in the tech industry, a lot of AI tools were emerging and with that, some AI website builders But the results seemed way too generic to us. It felt like the developers were rushing to catch the wave instead of building a proper tool We took our time, did months of RnD and finally came up with something better than what others in the market are doing. It’s got better design output. While it’s still in beta, I wanted to show HN what we did. Will appreciate the feedback when you guys try it out. Here is the link to signup for the beta:…
- IGI gamified AI logo generation for better designs2024 · app.owlai.art · ▲7
I recently quit my job at a decent TTS company I was working for as a software developer advocate to pursue what I have always enjoyed doing, which is creating software that is helpful. Before and after quitting my job, I have always found it expensive and time-consuming to hire a designer that can come up with a decent logo for my software, and as a software engineer, I really enjoy coding, not designing. One day, I made a pretty bold move to design a logo, and it took me a whole day to come up with a logo that looks nice. This is the reason I built Owl AI, a logo generator that generates…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
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
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
