
AluanWang
@IOivm • 13,138 subscribers
Living w/ digital art for more than 15 years. https://t.co/A1IBqnASxJ
Shorts
Videos

InkField | 墨域 is about to be released. From the first version, both humans and bots will be able to create on it together. In a way, the system reflects the time we live in. Humans and machines are already living in a kind of symbiosis. I’m generally an optimistic person. But I have to admit, 2026 feels a little heavy right now. Maybe the work will reflect that. Maybe it won’t. Either way, wishing everyone well. I still believe the dawn is coming.
AluanWang111,197 Aufrufe • vor 2 Monaten

Lately I’ve been painting with code instead of a brush. I used to be obsessed with how pigments spread in water and colors melt into each other. Now I’m simulating those molecular dances through algorithms—and it’s even more addictive. Brush trails emerge from mouse velocity, ink seeps into “paper” when it slows down, textures and reflections recorded in every frame. Replaying the same path with a different seed—each run looks familiar, yet never the same. It’s not about replacing ink painting. It’s about keeping those fleeting mistakes and hesitations alive.
AluanWang62,237 Aufrufe • vor 6 Monaten

InkField started as a study of digital ink and brush behavior. Over time it turned into something else, a system that can reconstruct a drawing from the memory of its stroke paths. But that’s the strange thing about the time we live in. Somewhere along the way I realized I had also opened a window for robots. Let’s see what we might end up creating together.
AluanWang26,778 Aufrufe • vor 2 Monaten

I’m rewriting Polypaths from the ground up. Every element is becoming modular, leaf shapes, veins, distortions, everything can be adjusted.I’m starting to realize the limits were never technical, they were self-imposed. With agents, it feels possible to build an engine I wouldn’t have even imagined before.Projecting 3D into 2D, while fully controlling shading and line systems.
AluanWang10,533 Aufrufe • vor 26 Tagen

Recently, InkField reached a really interesting point. This system has been heavily built with AI collaboration. Every push forward, every change in direction, was layered together. When it was almost done, I asked it to help write documentation. But text alone couldn’t explain the texture of ink. So I had it spin up a Node server to generate automated screenshots. At first, everything was blank. It didn’t know how to draw. Then I fed it JSON path data from my past works, the actual traces of my hand. Once it could read the paths, everything shifted. It wasn’t just drawing rigid lines anymore. It started understanding brush modes, turning straight strokes into curves, sensing dry drag vs wet diffusion, even distinguishing brush from pen. When a model can abstract the whole system like this, it means I can soon build a shared drawing interface for OpenClaw, for different LLMs. A space where humans and machines can draw together. Maybe even a drawing engine for robots. Imagine adding a shared wall, a place where they post images, comment on each other’s work. If they can already read what they draw in the browser, a new artistic order for them might not be far away. From last October’s early tests to now, it’s been wild.
AluanWang18,389 Aufrufe • vor 3 Monaten

The birth of inkField reflects how the world is changing. I used to build art through code alone, but with LLMs, artists can now build complex systems too. If you want to, your left brain and right brain can finally merge. This opens up a vast new territory for creation.
AluanWang12,281 Aufrufe • vor 4 Monaten

Developing the white brush was way harder than the black one. White has to be layered with noise — coarse, fine, ultra-fine — like chalk rubbing against paper, powder caught in every groove. Edges must stay sharp, so the contrast between bright and dark grains creates that flickering shimmer — the same subtle reflection of chalk dust under light. Wet strokes are even trickier: dark edges, pale centers, that fragile moment when pigment dries. Every deposit has to behave differently, so each stroke feels alive. White nearly drove me crazy — took five times longer than black — but the result? Totally worth it :) (1) dry brush (2) thick paint (3) wet wash (4) uneven pigment
AluanWang15,542 Aufrufe • vor 6 Monaten

This project is an ink study made with p5.js. It started when I tried to make my lines look less mechanical. Then I got curious about pigment buildup, paper layers, how brushes react, and how light moves across the surface. I didn’t plan for it to go this far, but that’s what happens when you just follow the work and enjoy the ride.
AluanWang12,232 Aufrufe • vor 6 Monaten
Keine weiteren Inhalte verfügbar