cs.HCNov 9, 2026

reComposer: Editable Planning for Controllable Image Generation

Authors: Susie S. Y. Li, Angie Boggust, Fred Hohman, Donghao Ren, Dominik Moritz, Yannick Assogba

Organizations: Tufts University Medford, MA, USA · Apple Cambridge, MA, USA · Apple Seattle, WA, USA · Apple Pittsburgh, PA, USA

Abstract

Prompt-based image generation makes it easy to produce visual assets, but offers little support for engaging with the creative process. Prompting collapses interdependent creative decisions into a monolithic instruction and returns a finished image, leaving control limited to revising the prompt or correcting the model's output. We present reComposer, a process-oriented image-generation interface built around editable planning, which decomposes users' evolving intent into meaningful creative decisions - such as subject, composition, or palette - and collaborates with users to explore underspecified goals and alternatives. reComposer supports conversational and direct manipulation of the plan, moving between concept-level intent and visual-level control. We evaluated reComposer with 8 design and non-design professionals. Compared to prompting, participants felt greater control and ownership while developing visual assets, exploring alternatives, and iterating on details. Our findings suggest how shifting generative AI interaction from specifying outputs to shaping process can support creative thinking alongside asset production.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation

    Apr 15, 2026Zoe De Simone, Angie Boggust, Fredo Durand +2T2I GenerationImage Generation

  2. DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable

    Aug 1, 2026Pu Cao, Qingye Kong, Xuedan Yin +5Image Reconstruction

  3. Design Generative AI for Practitioners: Exploring Interaction Approaches Aligned with Creative Practice

    Mar 3, 2026Xiaohan Peng, Wendy E. Mackay, Janin KochMixed-Initiative InteractionHuman-AI Interaction