Poetry2Image: An Iterative Correction Framework for Images Generated from Chinese Classical Poetry
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917715323650048 |
|---|---|
| author | Jiang, Jing Ling, Yiran Li, Binzhu Li, Pengxiang Piao, Junming Zhang, Yu |
| author_facet | Jiang, Jing Ling, Yiran Li, Binzhu Li, Pengxiang Piao, Junming Zhang, Yu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06196 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Poetry2Image: An Iterative Correction Framework for Images Generated from Chinese Classical Poetry Jiang, Jing Ling, Yiran Li, Binzhu Li, Pengxiang Piao, Junming Zhang, Yu Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Poetry2Image: An Iterative Correction Framework for Images Generated from Chinese Classical Poetry |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.06196 |