Klad - Paint app your coding agent can drive
Show HN: Klad, a paint app your coding agent can drive (source-available)
Klad is a 2D painting and animation app built for collaboration between humans and coding agents. You paint with a pen in the editor, while your agent paints through the `klad` command line using the same brushes and layers. Every stroke, fill, and shape remains editable data, so you can tweak any detail later without rerolling. The app includes a full animation suite with timelines, in-betweens, bones, and game exports. Drawings are stored as plain files on your computer, making them Git-friendly. Klad is source-available and free for personal use or companies under €500k revenue. Try it by cloning the repo and building from source.
There is no image model in klad. Your agent decides what to paint; klad gives it brushes, layers and a timeline. Whatever either of you puts down stays what it was: a stroke with its path, pressure, brush and colour, a shape with its points, a fill with its region. So there's no rerolling and hoping for the best: if one leaf looks off, you fix that leaf.
- vunderba
Nice job~~
So I've done a little bit of testing. When I loaded up the editor, I expected it to communicate with the installed binaries for my large language models, or possibly use a BYOK (bring your own key) approach. But once I understood that it's driven from the command line and you see the changes happen in the editor that gets spun up, I had no problems.
I've been experimenting a fair amount with LLMs driving procedural graphics myself, although my experiments have been mostly limited to relatively low-resolution stuff, such as EGA adventure game graphics.
So I decided to put Klad through a relatively hard test: I took a reference picture of an illustrated squirrel and asked it to recreate it, then set up the rigging for a basic walk cycle. This was using Fable 5.2 high.
Then I did the same thing, but with a more traditional approach, using standard generative models to manually create a walk cycle. This was all done relatively quickly, so bear that in mind.
Here are the results. I still think these are early days, and LLM-driven graphics are only going to improve.
And there are obvious advantages to a procedural system with rigging: Much easier to maintain consistency, palette control, and the ability to make precise alterations without having to deal with any kind of conventional in-painting nonsense.
- mmvvaa
I have been meaning to find/build a tool that would sit in between the pre-production assets of a movie clip (script, characters, locations, prop assets) and the moment you press generate.
I envisioned it as some sort of a flipbook that would allow me to *cheaply* get a low-res idea of what the 'generate' click would get me, without having to burn movie making tokens.
This may not be exactly it, but it nudged me into a direction. Thanks!
I will give it a try and report back.
- ImJasonH
This is pretty fun! I had an agent (Opus 5.5) poke around and make some characters which are less obviously LLM-generated than what you normally see.