Search papers, labs, and topics across Lattice.
This paper introduces narrative keyframing, an innovative interaction technique that allows writers to impose various narrative constraints at specific moments in their stories, enhancing AI-assisted creative writing. By employing three types of keyframes鈥攑lot, character, and perspective鈥攖he method provides a dynamic framework for connecting story planning with adaptive text generation, enabling writers to exert fine-grained control over narrative elements. User studies demonstrate that narrative keyframing significantly improves the controllability, transparency, and engagement of generative AI in the creative writing process.
Writers can now exert unprecedented control over AI-generated narratives by specifying keyframes that shape plot, character development, and perspective.
We introduce narrative keyframing, an interaction technique for AI-assisted creative writing that lets writers specify different types of narrative constraints at selected moments in a story, then use AI to generate intervening prose. Inspired by the use of keyframing in animation, narrative keyframing offers a flexible way to connect story planning with adaptive control over generated text. We explore three types of keyframes: plot keyframes define significant events in a story, character keyframes represent how individual characters change over the narrative, and perspective keyframes capture how individual characters experience different events through first-person narratives. Plot and character keyframes offer a flexible way to adapt the type of high-level conditioning explored in previous AI writing tools to more customizable, iterative, and fine-scale control, while perspective keyframes add a new way to control characterization and focalization by using first-person narratives as an intermediary. Through a user study, we show that narrative keyframing supports a more controllable, transparent, and engaging way to use generative AI in creative writing.
