Poetry2Image: An Iterative Correction Framework for Images Generated from Chinese Classical Poetry

TL;DR

Poetry2Image is an iterative correction framework that improves Chinese classical poetry image generation by automating feedback and correction, significantly enhancing element completeness and semantic consistency without extensive fine-tuning.

Contribution

The paper introduces a novel iterative correction framework utilizing external poetry datasets and large language models to improve image generation quality from Chinese classical poetry.

Findings

Achieves 70.63% element completeness, 25.56% improvement over direct generation.

Attains 80.09% semantic consistency in generated images.

Effective across five popular image generation models.

Abstract

Text-to-image generation models often struggle with key element loss or semantic confusion in tasks involving Chinese classical poetry.Addressing this issue through fine-tuning models needs considerable training costs. Additionally, manual prompts for re-diffusion adjustments need professional knowledge. To solve this problem, we propose Poetry2Image, an iterative correction framework for images generated from Chinese classical poetry. Utilizing an external poetry dataset, Poetry2Image establishes an automated feedback and correction loop, which enhances the alignment between poetry and image through image generation models and subsequent re-diffusion modifications suggested by large language models (LLM). Using a test set of 200 sentences of Chinese classical poetry, the proposed method--when integrated with five popular image generation models--achieves an average element completeness of 70.63%, representing an improvement of 25.56% over direct image generation. In tests of semantic correctness, our method attains an average semantic consistency of 80.09%. The study not only promotes the dissemination of ancient poetry culture but also offers a reference for similar non-fine-tuning methods to enhance LLM generation.