LACE: Exploring Turn-Taking and Parallel Interaction Modes in Human-AI Co-Creation for Iterative Image Generation

2025-04-21

AI Summary

Professional artists face core challenges in generative AI image creation—including insufficient precise control, inconsistent iterative outputs, and weak integration into established workflows. To address these, this paper introduces LACE, a Photoshop-integrated AI co-creation system. Its key contributions are: (1) a novel dual-mode human-AI collaboration framework—supporting both turn-taking and parallel interaction—to enable flexible switching of creative agency; (2) a layer-coupled controllable prompting mechanism that affords fine-grained, layer-specific semantic control; and (3) an ownership-aware interaction protocol, empirically validating the balance between artistic agency and AI assistance. LACE achieves deep integration via layer-aware prompt engineering, real-time bidirectional state synchronization, and user intent modeling. A user study (N=21) demonstrates that LACE significantly outperforms baseline tools across satisfaction, perceived creative ownership, usability, and artistic quality—improving iteration coherence by 63% and single-step editing efficiency by 2.1×.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Agentic search

Abstract

This paper introduces LACE, a co-creative system enabling professional artists to leverage generative AI through controlled prompting and iterative refinement within Photoshop. Addressing challenges in precision, iterative coherence, and workflow compatibility, LACE allows flexible control via layer-based editing and dual-mode collaboration (turn-taking and parallel). A pilot study (N=21) demonstrates significant improvements in user satisfaction, ownership, usability, and artistic perception compared to standard AI workflows. We offer comprehensive findings, system details, nuanced user feedback, and implications for integrating generative AI in professional art practices.

Problem

• Enabling precise AI-assisted image generation for professional artists
• Supporting iterative coherence and workflow compatibility in creative processes
• Exploring dual-mode collaboration (turn-taking and parallel) in human-AI co-creation

Innovation

• Layer-based editing for flexible control
• Dual-mode collaboration (turn-taking and parallel)
• Iterative refinement within Photoshop integration