Loading...
Loading...
Available on 1 platform
Sign in to view source links and access this dataset
9,000 images generated for the novel task of multicultural text-to-image generation. The dataset forms the empirical foundation of the MosAIG framework introduced in the paper 'Multi-Agent Multimodal Models for Multicultural Text to Image Generation.' It was created by AIM-SCU and last updated on HuggingFace in April 2026.
License is unknown; terms of use must be verified before application.