MetaPrompter – Evolving Prompts

The dissemination of open-source text-to-image generative models and the increasing quality of their output has led to a growth in interest in the field. The quality of the images greatly depends on the prompt used, i.e. a phrase that includes descriptive terms to be used as input on text-to-image model. However, choosing the right prompt is a complex task, often relying on a trial-and-error approach.

In this project, we introduce an evolutionary approach to prompt generation where users begin by creating a blueprint for what might be a candidate prompt and then initiate an evolutionary process to interactively explore the space of prompts encoded by the initial blueprint and according to their preferences. Our work is a step towards a more dynamic and interactive way to generate prompts that lead to a wide variety of visual outputs, with which users can easily obtain prompts that match their goals.

You can find the Google Colab notebook at: https://colab.research.google.com/drive/1TF4BjmcyintiTm9NAYVEIAyof-Ps-um7?usp=sharing
 
 

Publications

• T. Martins, J. M. Cunha, J. Correia, and P. Machado, “Towards the Evolution of Prompts with MetaPrompter,” in (to be published in) Artificial Intelligence in Music, Sound, Art and Design – 12th International Conference, EvoMUSART 2023, Held as Part of EvoStar 2023, Brno, Czech Republic, April 12-14, 2023, Proceedings, 2023.

  • Bibtex
  @inproceedings{martins2023metaprompter,
  author = {Tiago Martins and Jo{\~{a}}o Miguel Cunha and Jo{\~{a}}o Correia and Penousal Machado},
  booktitle = {(to be published in) Artificial Intelligence in Music, Sound, Art and Design – 12th International Conference, EvoMUSART 2023, Held as Part of EvoStar 2023, Brno, Czech Republic, April 12-14, 2023, Proceedings},
  editor = {Colin Johnson and Nereida Rodr{\'{\i}}guez{-}Fern{\'{a}}ndez and S{\'{e}}rgio M. Rebelo},
  publisher = {Springer},
  title = {Towards the Evolution of Prompts with MetaPrompter},
  year = {2023}}
  • |
  • PDF