Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement

TL;DR

Culture-TRIP enhances text-to-image generation by iteratively refining prompts with cultural context retrieval, improving alignment for underrepresented cultural concepts using large language models and web data.

Contribution

Introduces a novel iterative prompt refinement method that incorporates cultural context retrieval to improve culturally-aware image generation.

Findings

Improved alignment between generated images and cultural prompts.

User survey confirms enhanced cultural relevance of images.

Effective use of Wikipedia and web data for cultural context retrieval.

Abstract

Text-to-Image models, including Stable Diffusion, have significantly improved in generating images that are highly semantically aligned with the given prompts. However, existing models may fail to produce appropriate images for the cultural concepts or objects that are not well known or underrepresented in western cultures, such as `hangari' (Korean utensil). In this paper, we propose a novel approach, Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement (Culture-TRIP), which refines the prompt in order to improve the alignment of the image with such culture nouns in text-to-image models. Our approach (1) retrieves cultural contexts and visual details related to the culture nouns in the prompt and (2) iteratively refines and evaluates the prompt based on a set of cultural criteria and large language models. The refinement process utilizes the information retrieved from Wikipedia and the Web. Our user survey, conducted with 66 participants from eight different countries demonstrates that our proposed approach enhances the alignment between the images and the prompts. In particular, C-TRIP demonstrates improved alignment between the generated images and underrepresented culture nouns. Resource can be found at https://shane3606.github.io/Culture-TRIP.