Preprint Open access
TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows
Recent text-to-image models have made substantial progress in photorealism, aesthetics, and text-image alignment. Yet visually appealing images can still violate real-world plausibility, exhibiting malformed object structures, impossible anatomy, physically implausible interactions, or inconsistent spatial relationship …