Publication | ACM UIST 2023
WorldSmith
Iterative and Expressive Prompting for World Building with a Generative AI
Abstract
WorldSmith: Iterative and Expressive Prompting for World Building with a Generative AI
Hai Dang, Frederik Brudy, George Fitzmaurice, Fraser Anderson
ACM UIST 2023
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 publicationRelated Resources
2024
Autodesk Demos Project Reframe at Colombia 4.0, Showcasing Animation InnovationLearn about a Project Reframe presentation and demo in Colombia,…
2023
Leveraging Graph Neural Networks for Graph Regression and Effective Enumeration ReductionGraph-based framework represents aspects of optimal thermal management…
2021
Inferring CAD Modeling Sequences using Zone GraphsIn computer-aided design (CAD), the ability to “reverse engineer” the…
2022
Data Visualization and Visual AnalyticsVisual data representations leverage the power of human perception to…
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