A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks

Trinh, Khoi; Seidenberger, Scott; Wijewickrama, Raveen; Jadliwala, Murtuza; Maiti, Anindya

doi:10.24963/ijcai.2025/1132

A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks

Khoi Trinh, Scott Seidenberger, Raveen Wijewickrama, Murtuza Jadliwala, Anindya Maiti

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. AI, Arts & Creativity. Pages 10189-10197.

https://doi.org/10.24963/ijcai.2025/1132

Keywords

Methods and resources: AI methods for better understanding human creative processes
Theory and philosophy of arts and creativity in AI systems: Social (multi-agent) creativity and human-computer co-creation
Methods and resources: AI systems for collaboration and co-creation
Application domains: Images, movies and visual arts

Abstract

With AI-generated content becoming widespread across digital platforms, it is important to understand how such content is inspired and produced. This study explores the underexamined task of image regeneration, where a human operator iteratively refines prompts to recreate a specific target image. Unlike typical image generation, regeneration begins with a visual reference. A key challenge is whether existing image similarity metrics (ISMs) align with human judgments and can serve as useful feedback in this process. We conduct a structured user study to evaluate how iterative prompt refinement affects similarity to target images and whether ISMs reflect the improvements perceived by human observers. Our results show that prompt adjustments significantly improve alignment, both subjectively and quantitatively, highlighting the potential of iterative workflows in enhancing generative image quality.

Khoi Trinh, Scott Seidenberger, Raveen Wijewickrama, Murtuza Jadliwala, and Anindya Maiti. 2025. A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10189–10197. https://doi.org/10.24963/ijcai.2025/1132

@inproceedings{ijcai2025p1132,
  title     = {A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks},
  author    = {Trinh, Khoi and Seidenberger, Scott and Wijewickrama, Raveen and Jadliwala, Murtuza and Maiti, Anindya},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {10189--10197},
  year      = {2025},
  month     = {8},
  note      = {AI, Arts & Creativity},
  doi       = {10.24963/ijcai.2025/1132},
  url       = {https://doi.org/10.24963/ijcai.2025/1132},
}

TY  - CPAPER
TI  - A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks
AU  - Trinh, Khoi
AU  - Seidenberger, Scott
AU  - Wijewickrama, Raveen
AU  - Jadliwala, Murtuza
AU  - Maiti, Anindya
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 10189
EP  - 10197
DO  - 10.24963/ijcai.2025/1132
UR  - https://doi.org/10.24963/ijcai.2025/1132
ER  -