CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation [NeurIPS 2025]

Kavana Venkatesh*, Connor Dunlop*, Pinar Yanardag

^{* Equal contribution}

We introduce CREA, an agentic framework that emulates the human creative process for creative image editing and generation. Our approach is driven by collaborative interactions between specialized agents, such as a Creative Director and an Art Critic, who communicate to refine and enhance creative output. Moreover, our approach can be extended to video domain for creative video generation. Our framework can also be integrated with personalization techniques to further enrich and expand creative workflows.

CREA proposes a collaborative multi-agent framework designed to emulate the human creative process for image editing and generation. CREA operates through four key stages: 1.a Pre-Generation Planning, where agents such as the Creative Director and Prompt Architect define a creativity blueprint and synthesize a contrastive, high-creativity prompt grounded in six creativity principles (e.g., originality, expressivness, aesthetic appeal, technical execution, unexpected associations, interpretability & depth). 1.b Creative Image Generation/Editing, where the Generative Executor uses text-to-image diffusion models or ControlNet to either generate new images or perform disentangled edits. 2. Post-Generation Evaluation, where an Art Critic agent, powered by a multimodal LLM, scores the output on the creativity dimensions to compute a Creativity Index (CI). 3. Self-Enhancement, where the Refinement Strategist suggests targeted improvements based on feedback, prompting iterative refinement via collaborative agent feedback loops. This structured and collaborative workflow enables CREA to generate and refine outputs that are novel, expressive, and artistically coherent, maximizing creativity and diversity.

conda create -n crea python=3.12
conda activate crea

pip install -e .

export OPENAI_API_KEY=<your openai api key here>

For generation python run.py --concept="couch"

For editing python run.py --edit_image="assets/couch.jpg"

To run multiple concepts bash run_batch.sh

Configurations can be adjusted in config_generation.yaml and config_editing.yaml

If you find our work beneficial for your research, please consider citing!

@inproceedings{venkatesh2025crea,
 author = {Venkatesh, Kavana and Dunlop, Connor and Yanardag, Pinar},
 booktitle = {Advances in Neural Information Processing Systems},
 pages = {171332--171392},
 publisher = {Curran Associates, Inc.},
 title = {CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation},
 url = {https://proceedings.neurips.cc/paper_files/paper/2025/file/fa41e9d5dfcc97cd9eed99f001aa28e5-Paper-Conference.pdf},
 volume = {38},
 year = {2025}
}