用多智能体协作模拟人类创作，实现有艺术感的图像生成与编辑。
CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation
- 多个专业智能体分角色协作：构思、生成、批评、优化图像。
- 在多样性、语义一致性和创意转化上超越现有方法。
- 适合对艺术创作、交互式图像生成感兴趣的开发者与设计师。
AI图像创作仍面临根本性挑战，不仅需生成视觉吸引人的内容，还需添加新颖、富有表现力和艺术性的变换。与依赖直接提示修改的传统编辑不同，创造性图像编辑需要一种自主、迭代的方法，在原创性、连贯性和艺术意图之间取得平衡。为此，我们提出CREA，一个模仿人类创作过程的新型多智能体协作框架。该框架通过一组专业化智能体动态协作，完成图像的概念化、生成、批判与增强。通过广泛的定性与定量评估，我们证明CREA在多样性、语义对齐和创意转化方面显著优于当前最优方法。据我们所知，这是首个提出创造性编辑任务的工作。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。