CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation
It addresses the problem of enhancing creativity in AI imagery for artists and designers, introducing a new task rather than being incremental.
The paper tackles the challenge of creative image editing by introducing CREA, a multi-agent collaborative framework that mimics human creativity, and demonstrates it significantly outperforms state-of-the-art methods in diversity, semantic alignment, and creative transformation.
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 requires 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.