SSP: A Simple and Safe automatic Prompt engineering method towards realistic image synthesis on LVM
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_ | 1866912293895274496 |
|---|---|
| author | Cheng, Weijin Liu, Jianzhi Deng, Jiawen Ren, Fuji |
| author_facet | Cheng, Weijin Liu, Jianzhi Deng, Jiawen Ren, Fuji |
| contents | Recently, text-to-image (T2I) synthesis has undergone significant advancements, particularly with the emergence of Large Language Models (LLM) and their enhancement in Large Vision Models (LVM), greatly enhancing the instruction-following capabilities of traditional T2I models. Nevertheless, previous methods focus on improving generation quality but introduce unsafe factors into prompts. We explore that appending specific camera descriptions to prompts can enhance safety performance. Consequently, we propose a simple and safe prompt engineering method (SSP) to improve image generation quality by providing optimal camera descriptions. Specifically, we create a dataset from multi-datasets as original prompts. To select the optimal camera, we design an optimal camera matching approach and implement a classifier for original prompts capable of automatically matching. Appending camera descriptions to original prompts generates optimized prompts for further LVM image generation. Experiments demonstrate that SSP improves semantic consistency by an average of 16% compared to others and safety metrics by 48.9%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01128 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SSP: A Simple and Safe automatic Prompt engineering method towards realistic image synthesis on LVM Cheng, Weijin Liu, Jianzhi Deng, Jiawen Ren, Fuji Computer Vision and Pattern Recognition Recently, text-to-image (T2I) synthesis has undergone significant advancements, particularly with the emergence of Large Language Models (LLM) and their enhancement in Large Vision Models (LVM), greatly enhancing the instruction-following capabilities of traditional T2I models. Nevertheless, previous methods focus on improving generation quality but introduce unsafe factors into prompts. We explore that appending specific camera descriptions to prompts can enhance safety performance. Consequently, we propose a simple and safe prompt engineering method (SSP) to improve image generation quality by providing optimal camera descriptions. Specifically, we create a dataset from multi-datasets as original prompts. To select the optimal camera, we design an optimal camera matching approach and implement a classifier for original prompts capable of automatically matching. Appending camera descriptions to original prompts generates optimized prompts for further LVM image generation. Experiments demonstrate that SSP improves semantic consistency by an average of 16% compared to others and safety metrics by 48.9%. |
| title | SSP: A Simple and Safe automatic Prompt engineering method towards realistic image synthesis on LVM |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.01128 |