Understanding the Impact of Negative Prompts: When and How Do They Take Effect?
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916274837127168 |
|---|---|
| author | Ban, Yuanhao Wang, Ruochen Zhou, Tianyi Cheng, Minhao Gong, Boqing Hsieh, Cho-Jui |
| author_facet | Ban, Yuanhao Wang, Ruochen Zhou, Tianyi Cheng, Minhao Gong, Boqing Hsieh, Cho-Jui |
| contents | The concept of negative prompts, emerging from conditional generation models like Stable Diffusion, allows users to specify what to exclude from the generated images.%, demonstrating significant practical efficacy. Despite the widespread use of negative prompts, their intrinsic mechanisms remain largely unexplored. This paper presents the first comprehensive study to uncover how and when negative prompts take effect. Our extensive empirical analysis identifies two primary behaviors of negative prompts. Delayed Effect: The impact of negative prompts is observed after positive prompts render corresponding content. Deletion Through Neutralization: Negative prompts delete concepts from the generated image through a mutual cancellation effect in latent space with positive prompts. These insights reveal significant potential real-world applications; for example, we demonstrate that negative prompts can facilitate object inpainting with minimal alterations to the background via a simple adaptive algorithm. We believe our findings will offer valuable insights for the community in capitalizing on the potential of negative prompts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_02965 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Understanding the Impact of Negative Prompts: When and How Do They Take Effect? Ban, Yuanhao Wang, Ruochen Zhou, Tianyi Cheng, Minhao Gong, Boqing Hsieh, Cho-Jui Computer Vision and Pattern Recognition The concept of negative prompts, emerging from conditional generation models like Stable Diffusion, allows users to specify what to exclude from the generated images.%, demonstrating significant practical efficacy. Despite the widespread use of negative prompts, their intrinsic mechanisms remain largely unexplored. This paper presents the first comprehensive study to uncover how and when negative prompts take effect. Our extensive empirical analysis identifies two primary behaviors of negative prompts. Delayed Effect: The impact of negative prompts is observed after positive prompts render corresponding content. Deletion Through Neutralization: Negative prompts delete concepts from the generated image through a mutual cancellation effect in latent space with positive prompts. These insights reveal significant potential real-world applications; for example, we demonstrate that negative prompts can facilitate object inpainting with minimal alterations to the background via a simple adaptive algorithm. We believe our findings will offer valuable insights for the community in capitalizing on the potential of negative prompts. |
| title | Understanding the Impact of Negative Prompts: When and How Do They Take Effect? |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.02965 |