CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation

Kavana Venkatesh, Connor Dunlop, Pinar Yanardag

Keywords: creativity, t2i, diffusion, multi-agentic systems, llm

TL;DR: We introduce the first work for disentangled creative editing with an agentic framework.

Abstract: Creativity in AI imagery remains a fundamental challenge, requiring not only the generation of visually compelling content but also the capacity to add novel, expressive, and artistically rich transformations to images. Unlike conventional editing tasks that rely on direct prompt-based modifications, creative image editing demands an autonomous, iterative approach that balances originality, coherence, and artistic intent. To address this, we introduce CREA, a novel multi-agent collaborative framework that mimics the human creative process. Our framework leverages a team of specialized AI agents who dynamically collaborate to conceptualize, generate, critique, and enhance images. Through extensive qualitative and quantitative evaluations, we demonstrate that CREA significantly outperforms state-of-the-art methods in diversity, semantic alignment, and creative transformation. To the best of our knowledge, this is the first work to introduce the task of creative editing.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 1955