Saved in:
Bibliographic Details
Main Authors: Jelaca, Aleksa, Jiao, Ying, Tian, Chang, Moens, Marie-Francine
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.21375
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914057086304256
author Jelaca, Aleksa
Jiao, Ying
Tian, Chang
Moens, Marie-Francine
author_facet Jelaca, Aleksa
Jiao, Ying
Tian, Chang
Moens, Marie-Francine
contents Text-to-image generation has advanced rapidly with large-scale multimodal training, yet fine-grained controllability remains a critical challenge. Counterfactual controllability, defined as the capacity to deliberately generate images that contradict common-sense patterns, remains a major challenge but plays a crucial role in enabling creativity and exploratory applications. In this work, we address this gap with a focus on counterfactual size (e.g., generating a tiny walrus beside a giant button) and propose an automatic prompt engineering framework that adapts base prompts into revised prompts for counterfactual images. The framework comprises three components: an image evaluator that guides dataset construction by identifying successful image generations, a supervised prompt rewriter that produces revised prompts, and a DPO-trained ranker that selects the optimal revised prompt. We construct the first counterfactual size text-image dataset and enhance the image evaluator by extending Grounded SAM with refinements, achieving a 114 percent improvement over its backbone. Experiments demonstrate that our method outperforms state-of-the-art baselines and ChatGPT-4o, establishing a foundation for future research on counterfactual controllability.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21375
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automated Prompt Generation for Creative and Counterfactual Text-to-image Synthesis
Jelaca, Aleksa
Jiao, Ying
Tian, Chang
Moens, Marie-Francine
Computer Vision and Pattern Recognition
Artificial Intelligence
Text-to-image generation has advanced rapidly with large-scale multimodal training, yet fine-grained controllability remains a critical challenge. Counterfactual controllability, defined as the capacity to deliberately generate images that contradict common-sense patterns, remains a major challenge but plays a crucial role in enabling creativity and exploratory applications. In this work, we address this gap with a focus on counterfactual size (e.g., generating a tiny walrus beside a giant button) and propose an automatic prompt engineering framework that adapts base prompts into revised prompts for counterfactual images. The framework comprises three components: an image evaluator that guides dataset construction by identifying successful image generations, a supervised prompt rewriter that produces revised prompts, and a DPO-trained ranker that selects the optimal revised prompt. We construct the first counterfactual size text-image dataset and enhance the image evaluator by extending Grounded SAM with refinements, achieving a 114 percent improvement over its backbone. Experiments demonstrate that our method outperforms state-of-the-art baselines and ChatGPT-4o, establishing a foundation for future research on counterfactual controllability.
title Automated Prompt Generation for Creative and Counterfactual Text-to-image Synthesis
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.21375