Powered by Midjourney

Midjourney Storytelling Lab

_

sailing boat

About Our Lab

We're a small group of researchers at Midjourney building expressive, approachable, and controllable tools for AI-supported storytelling. Current lab projects focus on collaborative worldbuilding, comics generation, and new interaction techniques for steering the generation of story text.

Recent work by lab members has been published at HCI and AI conferences including CHI, UIST, IUI, C&C, DIS, COLM, and ACL.

Lab Members

Max Kreminski

Max Kreminski

Research Scientist and Director

John Joon Young Chung

John Joon Young Chung

Research Scientist

Melissa Roemmele

Melissa Roemmele

Research Scientist

Uchan Sun

Uchan Sun

Research Artist

Tiffany Wang

Tiffany Wang

Research Engineer

Yi Wang

Yi Wang

Research Scientist

Shm Garanganao Almeda

Shm Garanganao Almeda

Visiting Researcher
(Summer 2025)

Brett A. Halperin

Brett A. Halperin

Visiting Researcher
(Summer 2025)

Yuwen Lu

Yuwen Lu

Visiting Researcher
(Summer 2025)

Taewook Kim

Taewook Kim

Visiting Researcher
(Spring-Summer 2024)

Alex Calderwood

Alex Calderwood

Visiting Researcher
(Summer-Fall 2024)

Selected Projects

Patchwork Patchwork (animated)

Patchwork

A collaborative, AI-supported infinite canvas for creating fictional worlds.

Related Publications
Modifying Large Language Model Post-Training for Diverse Creative Writing

Modifying Large Language Model Post-Training for Diverse Creative Writing

Language model post-training techniques for enhancing diversity while maintaining quality in creative writing.

Phraselette: A Poet’s Procedural Palettes

Phraselette: A Poet’s Procedural Palettes

An AI-powered artistic material writing support interface that helps experimental poets search for words and phrases.

Fuzzy Linkography: Automatic Graphical Summarization of Creative Activity Traces

Fuzzy Linkography: Automatic Graphical Summarization of Creative Activity Traces

A means of automatically tracing and analyzing creative moves via a “fuzzy” computational model of semantic similarity.

Toyteller: AI-Powered Visual Storytelling Through Toy-Playing with Character Symbols Toyteller: AI-Powered Visual Storytelling Through Toy-Playing with Character Symbols (animated)

Toyteller: AI-Powered Visual Storytelling Through Toy-Playing with Character Symbols

A novel AI-based interface for playful storytelling: users steer the generation of story text by physically acting out a scene with abstract shapes, as if playing with toys.

Drama Llama: An LLM-Powered Storylets Framework for Authorable Responsiveness in Interactive Narrative

Drama Llama: An LLM-Powered Storylets Framework for Authorable Responsiveness in Interactive Narrative

An LLM-powered storylets framework that supports the authoring of responsive, open-ended interactive stories.

Patchview: LLM-Powered Worldbuilding with Generative Dust and Magnet Visualization Patchview: LLM-Powered Worldbuilding with Generative Dust and Magnet Visualization (animated)

Patchview: LLM-Powered Worldbuilding with Generative Dust and Magnet Visualization

A customizable LLM-powered system that visually aids worldbuilding by allowing users to interact with story concepts and elements through the physical metaphor of magnets and dust.

A Design Space for Intelligent and Interactive Writing Assistants

A Design Space for Intelligent and Interactive Writing Assistants

A research addressing the fragmentation across writing assistant technologies by developing a structured design space through systematic review across five key dimensions: task, user, technology, interaction, and ecosystem.