Prompt Refinement with Image Pivot for Text-to-Image Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913409424949248 |
|---|---|
| author | Zhan, Jingtao Ai, Qingyao Liu, Yiqun Pan, Yingwei Yao, Ting Mao, Jiaxin Ma, Shaoping Mei, Tao |
| author_facet | Zhan, Jingtao Ai, Qingyao Liu, Yiqun Pan, Yingwei Yao, Ting Mao, Jiaxin Ma, Shaoping Mei, Tao |
| contents | For text-to-image generation, automatically refining user-provided natural language prompts into the keyword-enriched prompts favored by systems is essential for the user experience. Such a prompt refinement process is analogous to translating the prompt from "user languages" into "system languages". However, the scarcity of such parallel corpora makes it difficult to train a prompt refinement model. Inspired by zero-shot machine translation techniques, we introduce Prompt Refinement with Image Pivot (PRIP). PRIP innovatively uses the latent representation of a user-preferred image as an intermediary "pivot" between the user and system languages. It decomposes the refinement process into two data-rich tasks: inferring representations of user-preferred images from user languages and subsequently translating image representations into system languages. Thus, it can leverage abundant data for training. Extensive experiments show that PRIP substantially outperforms a wide range of baselines and effectively transfers to unseen systems in a zero-shot manner. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_00247 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prompt Refinement with Image Pivot for Text-to-Image Generation Zhan, Jingtao Ai, Qingyao Liu, Yiqun Pan, Yingwei Yao, Ting Mao, Jiaxin Ma, Shaoping Mei, Tao Computer Vision and Pattern Recognition For text-to-image generation, automatically refining user-provided natural language prompts into the keyword-enriched prompts favored by systems is essential for the user experience. Such a prompt refinement process is analogous to translating the prompt from "user languages" into "system languages". However, the scarcity of such parallel corpora makes it difficult to train a prompt refinement model. Inspired by zero-shot machine translation techniques, we introduce Prompt Refinement with Image Pivot (PRIP). PRIP innovatively uses the latent representation of a user-preferred image as an intermediary "pivot" between the user and system languages. It decomposes the refinement process into two data-rich tasks: inferring representations of user-preferred images from user languages and subsequently translating image representations into system languages. Thus, it can leverage abundant data for training. Extensive experiments show that PRIP substantially outperforms a wide range of baselines and effectively transfers to unseen systems in a zero-shot manner. |
| title | Prompt Refinement with Image Pivot for Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.00247 |