adamhowell

Claude and I have spent most of the summer on exactly this problem for Skechworks (skechworks.com), a free little Mac design app I made to help my own workflow that is very similar to yours. I use it for my custom coin shop The Achieve Mint (theachievemint.com).

It runs VTracer under the hood too. Most of the cleanup you're doing in Inkscape could possibly be pushed to before and after the trace?

Skechworks picks the palette before the trace and forces it again after. I quantize to 8 colors with pngquant, trace, then snap every fill back to the nearest palette color. VTracer fills each region with its own average color, otherwise you get hundreds of nearly identical grays. One design went from 279 fill colors to 3.

I upscale 2x before I quantize. The anti-aliasing is what tells the tracer where an edge really sits. Quantize at 1x and you throw that away, and small text comes out lumpy. Related gotcha: filter_speckle is an area, so don't double it when you double the image.

I also flatten transparency onto white first. VTracer counts every alpha value as a different color. I had a 5 color picture that it saw as 688 colors, and the trace took 6 GB of memory. Flattened, the same picture took 300 MB.

For the background I sample the whole edge of the picture. If 85% of it is one color, I delete every path in that color that touches the edge. White inside the drawing never touches the edge, so it stays.

For black and white I threshold with Otsu, then trace in color mode with hierarchical stacked instead of bw mode. bw mode hands you one giant black path full of holes. Stacked gives you every region as its own shape, which is much easier to edit. You have to pad the image with the background color first, or VTracer decides your subject is the canvas.

Your FLUX step is the same trick I use for photos and messy art. I have an image model redraw the picture as flat art, then trace the redraw. That came out about a quarter the file size of the best direct trace I could get. The catch is that the model moves and resizes the subject a little every run. I measure the box around the ink in both pictures and fit the trace back onto the original.

What I haven't solved is curve fitting. vectorizer.ai gives you real arcs and straight lines. VTracer gives you splines, so circles are never quite circles.

Something I discovered recently: if you stop following everyone you’re connected to, Linkedin’s feed breaks so you get this by default. I can still interact with everyone normally, send messages, etc, but I do not see any Linkedin content, ads, etc. Do not miss it.

Opus 5 Pelican SVG: https://pelocan.ai/drawings/ese0s599

So, on the one hand, I want everyone to be able to vibe code all the software they always wish existed and be able to use it and enjoy it.

But, on the other hand, I don't ever want to use anyone else's vibe coded software. Especially if it's non-essential.

And I certainly won't ever pay for it.

Gold has gone up 8% but just yesterday I conservatively updated the value by 4%

He did not! It was all still there. Too slippery for his tiny hands!

Stressful but yeah so far lots of fun.

Yeah it's a good question, because it's important to start with as much of a jolt as you can.

I launched the hunt the same day it got covered in a local popular Charlotte NC newsletter:

https://tinymoney.com/2025/10/09/treasure-hunt-nc-gold-coins...

So that helped kickstart it and was always part of the plan when I decided to actually do it.

Maybe some? But the circle today will be 160 miles wide or about the same width as Switzerland and Denmark. So I'm not sure how much shadows would help you pinpoint a specific location in an entire country worth of mountains.

Thanks! Yeah, I unfortunately can't shell out a straight $20k donation, but I saved the $25k over the year from my e-commerce business and justified it as a marketing expense if worse case scenario happens and it's found earlier than the math predicts. But if we get past break even then can't wait to write that check to help out the communities around here that are still recovering.

This one's going to be out of left field, but last Thursday I launched Countdown Treasure (https://countdowntreasure.com)

It's a real life treasure hunt in the Blue Ridge Mountains with a current total prize of $31,200+ in gold coins and a growing side pot.

I modeled it off of last year's Project Skydrop (https://projectskydrop.com) which was in the Boston area.

* Shrinking search area (today, Day 5, it will be 160 miles, on Day 21 it'll be just 1 foot wide)

* 24/7 webcam trained on the jar of gold coins sitting on the forest floor just off a public hiking trail

* Premium upgrades ($10 from each upgrade goes towards the side pot) for aerial photos above the treasure and access to a private online community (and you get your daily clues earlier)

* $2 from each upgrade goes towards the goal of raising $20k for continued Hurricane Helene relief

So far the side pot is $6k and climbing.

It's been such a fun project to work on, but also a lot of work. Tons of moving parts and checking twice and three times to make sure you've scrubbed all the EXIF data, etc.

> Lack of a mobile app. Minimalist design is great, but I still want an app to manage charging and be alerted to any vehicle issues.

At the 6 mins and 40 seconds timestamp on this video (https://youtu.be/cq1qEjwSYkw?t=400) he shows the car app that will tell you current range, etc

I think this is technically "image variations" and I think image variations are still only dall-e 3 for now (best I could tell earlier today from the API)

So, I've long dreamed of building an AI-powered https://iconfinder.com.

I started Accomplice v1 back in 2021 with this goal in mind and raised some VC money but it was too early.

Now, with these latest imagen-3.0-generate-002 (Gemini) and gpt-image-1 (OpenAI) models – especially this API release from OpenAI – I've been able to resurrect Accomplice as a little side project.

Accomplice v2 (https://accomplice.ai) is just getting started back up again – I honestly decided to rebuild it only a couple weeks ago in preparation for today once I saw ChatGPT's new image model – but so far 1,000s of free to download PNGs (and any SVGs that have already been vectorized are free too (costs a credit to vectorize)).

I generate new icons every few minutes from a huge list of "useful icons" I've built. Will be 100% pay-as-you-go. And for a credit, paid users can vectorize any PNGs they like, tweak them using AI, upload their own images to vectorize and download, or create their own icons (with my prompt injections baked in to get you good icon results)

Do multi-modal models make something like this obsolete? I honestly am not sure. In my experience with Accomplice v1, a lot of users didn't know what to do with a blank textarea, so the thinking here is there's value in doing some of the work for them upfront with a large searchable archive. Would love to hear others' thoughts.

But I'm having fun again either way.

Location: Charlotte, NC

Remote: Yes

Willing to relocate: No

Technologies: Ruby on Rails, Stimulus JS, Postgres, Tailwind CSS

Résumé/CV: https://www.linkedin.com/in/badamhowell / https://github.com/adamhowell

Email: [email protected]

Former Googler, VC-backed AI founder. Currently running my own e-commerce business. Lifetime startupper, hybrid frontend / backend designer and developer, who loves building intuitive products with Rails, Stimulus and Tailwind.

The other day I noticed shipitsquirrel.com was available, so I spent a couple evenings pair programming with ChatGPT to make a fun little Missile Command style game where you help Ship It Squirrel ship by blowing up distractions ;)

https://shipitsquirrel.com

No. Daniel Elk was a CTO and then freelance developer and Martin Lorentzon was co-founder of a digital marketing company (and the initial money)

I'm guessing this is the Twitter link you meant: https://twitter.com/TizzyEnt/status/1569439160561442817