Can World Models Generate Films? AI World Model and the Boundaries of Interactive Cinema
Abstract
This paper asks whether AI world models can generate films, and more specifically whether they can produce a form of interactive cinema in which viewers intervene in unfolding images. Drawing on André Bazin's account of cinema's founding desire for "a total and complete representation of reality," it situates contemporary world models such as LingBot-World, Happy Oyster, Runway's GWM-1, and Odyssey within a longer history of attempts to reproduce the world through moving images. The paper compares world models with virtual production, using the author's own AI-built lighting simulator as a case study of real-time light and shadow generation and its computational limits. It then reframes AI photography as a probabilistic mode of generation that repositions the photographer as a player exploring a space of possible outcomes rather than an author of a single fixed image. Finally, it turns to the material conditions of world models within the Anthropocene, following Kate Crawford's account of AI as an extractive industry, to argue that computing power, training data, and copyright are inseparable from questions of energy, labor, and planetary cost. The paper concludes that world models can already generate footage assembled into a finished film, but genuinely interactive cinema remains bounded by these material and infrastructural constraints.
References
- Bazin, A. (1967). The myth of total cinema. In H. Gray (Trans.),What is cinema?(Vol. 1, pp. 17–22). University of California Press. (Original work published 1958)
- Cameron, O. (2026, February 17).Why we must build world models. Odyssey. https://odyssey.ml/why-we-must-build-world-models
- Odyssey. (n.d.).Odyssey. Retrieved September 10, 2026, from https://odyssey.ml/
- Cameron, O. (2025, May 28).Introducing Odyssey-1: A playable world model. Odyssey. https://odyssey.ml/introducing-odyssey-1
- Robbyant Team. (n.d.).LingBot-World: Advancing open-source world models[Code repository]. GitHub. Retrieved September 10, 2026, from https://github.com/Robbyant/lingbot-world
- Happy Oyster. (n.d.).Happy Oyster: Real-time world model for interactive creation. Retrieved September 10, 2026, from https://www.happyoyster.com/
- Alibaba Cloud Community. (2026, April 20).Alibaba launches HappyOyster, a world model product for real-time immersive creation and interaction. Alibaba Cloud. https://www.alibabacloud.com/blog/alibaba-launches-happyoyster-a-world-model-product-for-real-time-immersive-creation-and-interaction_603048
- Runway. (2025, December 11).Introducing GWM-1. https://runway.com/research/introducing-runway-gwm-1
- Swords, J., & Willment, N. (2024). The emergence of virtual production – A research agenda.Convergence: The International Journal of Research into New Media Technologies, 30(5), 1557–1574. https://doi.org/10.1177/13548565241253903
- Reggio, G. (Director). (1982).Koyaanisqatsi[Film]. Institute for Regional Education.
- Crawford, K. (2021).Atlas of AI: Power, politics, and the planetary costs of artificial intelligence. Yale University Press.