DeckFlow: Iterative Specification on a Multimodal Generative Canvas

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Croisdale, Gregory, Huang, Emily, Chung, John Joon Young, Guo, Anhong, Wang, Xu, Henley, Austin Z., Omar, Cyrus
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909652974829568
author Croisdale, Gregory
Huang, Emily
Chung, John Joon Young
Guo, Anhong
Wang, Xu
Henley, Austin Z.
Omar, Cyrus
author_facet Croisdale, Gregory
Huang, Emily
Chung, John Joon Young
Guo, Anhong
Wang, Xu
Henley, Austin Z.
Omar, Cyrus
contents Generative AI promises to allow people to create high-quality personalized media. Although powerful, we identify three fundamental design problems with existing tooling through a literature review. We introduce a multimodal generative AI tool, DeckFlow, to address these problems. First, DeckFlow supports task decomposition by allowing users to maintain multiple interconnected subtasks on an infinite canvas populated by cards connected through visual dataflow affordances. Second, DeckFlow supports a specification decomposition workflow where an initial goal is iteratively decomposed into smaller parts and combined using feature labels and clusters. Finally, DeckFlow supports generative space exploration by generating multiple prompt and output variations, presented in a grid, that can feed back recursively into the next design iteration. We evaluate DeckFlow for text-to-image generation against a state-of-practice conversational AI baseline for image generation tasks. We then add audio generation and investigate user behaviors in a more open-ended creative setting with text, image, and audio outputs.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15873
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeckFlow: Iterative Specification on a Multimodal Generative Canvas
Croisdale, Gregory
Huang, Emily
Chung, John Joon Young
Guo, Anhong
Wang, Xu
Henley, Austin Z.
Omar, Cyrus
Human-Computer Interaction
Generative AI promises to allow people to create high-quality personalized media. Although powerful, we identify three fundamental design problems with existing tooling through a literature review. We introduce a multimodal generative AI tool, DeckFlow, to address these problems. First, DeckFlow supports task decomposition by allowing users to maintain multiple interconnected subtasks on an infinite canvas populated by cards connected through visual dataflow affordances. Second, DeckFlow supports a specification decomposition workflow where an initial goal is iteratively decomposed into smaller parts and combined using feature labels and clusters. Finally, DeckFlow supports generative space exploration by generating multiple prompt and output variations, presented in a grid, that can feed back recursively into the next design iteration. We evaluate DeckFlow for text-to-image generation against a state-of-practice conversational AI baseline for image generation tasks. We then add audio generation and investigate user behaviors in a more open-ended creative setting with text, image, and audio outputs.
title DeckFlow: Iterative Specification on a Multimodal Generative Canvas
topic Human-Computer Interaction
url https://arxiv.org/abs/2506.15873