Automated Prompt Generation for Creative and Counterfactual Text-to-image Synthesis
This work addresses a critical gap in fine-grained controllability for creative and exploratory applications in text-to-image synthesis, though it is incremental as it builds on existing methods like Grounded SAM.
The paper tackles the challenge of counterfactual controllability in text-to-image generation, specifically for size contradictions, by introducing an automated prompt engineering framework that outperforms state-of-the-art baselines and ChatGPT-4o.
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.