Creating AI art using a Raspberry Pi Zero 2 W shouldn’t work, but a determined software optimiser, Vito Plantamura, found a way.

What we’ve seen little of, to date, is canny AI generators that can run on a computer with modest processing capabilities. Training AI models requires powerful servers and multiple dedicated GPU (graphics processing unit) boards to create the model that can generate images.

fter this training process comes “inference”, where a trained model is used to infer a result on a regular computer. Even this takes time on a powerful computer with multiple GBs of RAM.

OnnxStream, however, makes inference possible on a tiny Raspberry Pi Zero with just 512MB RAM and finds a balance between processing power and generation time to turn out impressive imagery via Stable Diffusion.

See the video below and more via this article and on GitHub.