Publication | ACM UIST 2023


Iterative and Expressive Prompting for World Building with a Generative AI


WorldSmith: Iterative and Expressive Prompting for World Building with a Generative AI

Hai Dang, Frederik Brudy, George Fitzmaurice, Fraser Anderson


Crafting a rich and unique environment is crucial for fictional world-building, but can be difficult to achieve since illustrating a world from scratch requires time and significant skill. We investigate the use of recent multi-modal image generation systems to enable users iteratively visualize and modify elements of their fictional world using a combination of text input, sketching, and region-based filling. WorldSmith enables novice world builders to quickly visualize a fictional world with layered edits and hierarchical compositions. Through a formative study (4 participants) and first-use study (13 participants) we demonstrate that WorldSmith offers more expressive interactions with prompt-based models. With this work, we explore how creatives can be empowered to leverage prompt-based generative AI as a tool in their creative process, beyond current “click-once” prompting UI paradigms.

Download publication

Related Resources



From Steps to Stories with The Bentway

Check out how we’re using data to tell stories with The Bentway…



Evolving Through the Looking Glass: Learning Improved Search Spaces with Variational Autoencoders.

Nature has spent billions of years perfecting our genetic…



OrgOrgChart: The Evolution of an Organization

This project looks at the evolution of a company’s structure over…



Software Learning

This learning project investigates advanced techniques for assisting…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us