AI-Driven Creative Workflows

The field of human-AI collaboration is witnessing significant advancements, with a growing focus on developing innovative tools and frameworks that seamlessly integrate AI-generated content with human creativity. Researchers are exploring novel approaches to co-creative workflows, enabling professionals to leverage AI-driven generation and refinement capabilities to enhance their artistic and writing processes. A key direction in this field is the development of interactive and iterative systems that facilitate synchronized human-AI collaboration, allowing for more precise control over generated content and improved user experience. Noteworthy papers in this area include: Script2Screen, which presents an AI-assisted tool for scriptwriting with interactive audiovisual generation, and LACE, a co-creative system enabling professional artists to leverage generative AI through controlled prompting and iterative refinement. Twin-Co is also a notable framework that leverages synchronized, co-adaptive dialogue to progressively refine image generation. Additionally, a multi-agent framework for automated Qinqiang opera script generation showcases the potential of AI-driven pipelines in preserving traditional performing arts.

Sources

Script2Screen: Supporting Dialogue Scriptwriting with Interactive Audiovisual Generation

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

Twin Co-Adaptive Dialogue for Progressive Image Generation

LACE: Controlled Image Prompting and Iterative Refinement with GenAI for Professional Visual Art Creators

A Multi-Agent Framework for Automated Qinqiang Opera Script Generation Using Large Language Models

Built with on top of