By Stefania Druga, Ph.D. and Keith Hammond

Imagine the Star Trek replicator exists, and you can use it to create or replicate any object. What would you ask it to make? Would you print ready-made things, or prefer instead to get parts you can assemble, polish, and customize?

Generative AI is the closest approximation of the replicator we currently have — powerful artificial intelligence models that can synthesize images, text, video, code, and even 3D objects. Their results are primarily digital and still require quite a bit of shepherding to materialize in the physical world, but already it can be done — and we’re seeing a proliferation of new tools and improvements seemingly every day. 

How can we use generative AI models for tinkering and making? What are some initial forays in real, physical crafting with generative AI that can inspire future potential directions? This article sheds light on how generative AI works (in particular diffusion models), how we might ideate, design, and make with it, and what this all means for creators.