Looks great. This could be a form of image compression.

Several Amiga/DOS era games used a similar system for image compression.

Neat! I've followed you on Github. I like the idea of going to the past to see what works and adapting it for the LLM age. Nice work!

Thanks! Yeah, I started building it because I read an interview with the original creators of King’s Quest, Ken and Roberta Williams where they mentioned in passing that it was too expensive (in the 80s) from a storage perspective to store entire bitmaps for each scene, so instead they'd just store a series of very simple drawing instructions and render on demand.

I’m super excited to see more LLM-driven procedural graphics stuff in the future!

This is very cool! I will try your method for background and tile creation in the asset-generation tool I've built [1]. Would your procedural method work for animations as well, like sprites?

[1] https://github.com/acatovic/ai-game-studio

Hey armcat! I haven’t tried it extensively for generating sprite sheets, but here’s a quick attempt I made along with the prompt.

It works okay but you'd probably have to do a little bit of coaxing to get it to come out exactly right.

https://imgpb.com/TdaKjZK

Exactly, turn something nondeterministic into something more deterministic and AI does a great job at that.

I suspect your picscript language is an entirely unnecessary abstraction and the prompt (ie the model) is doing all the work.

How so? Judging from the examples the model does seem to take advantage of the language (creates and uses reusable elements) and AFAICT the language itself compiles down to "real" Sierra PIC commands so in theory it can be used with a Sierra PIC viewer/engine.

Yeah compiling to Sierra PIC is a unique advantage over asking the model for an image. But the claim im attacking is different. The claim in attacking is that you cant just tell it to produce images like this directly.

>As a result you end up sidestepping a lot of the problems with larger generative models, which can have issues with grid alignment, palette choices, and high-frequency noise.

All of these can be avoided with simple prompts and don’t require all this ceremony.

Convo then the artifact from the convo (sorry, apparently no way to share the pics but they are just captured from the artifact).

Convo: https://claude.ai/share/78cd63c8-ffdd-4569-8de2-ac8ab5c5cfe0

Artifact: https://claude.ai/artifact/3M6xiKJKz1oDxTKGWi8FUi

the style is completly differrent…

How so?

The difference i see is the shading. Could easily tell it to do flat fills instead.

Regardless it has none of the supposed problems of AI generated pixel art.

Here AGI means Adventure Game Interpreter.

AGI is here ... And always has been (Ken sent me).