Optimizing Negative Prompts for Enhanced Aesthetics and Fidelity in Text-To-Image Generation
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_ | 1866912105048834048 |
|---|---|
| author | Ogezi, Michael Shi, Ning |
| author_facet | Ogezi, Michael Shi, Ning |
| contents | In text-to-image generation, using negative prompts, which describe undesirable image characteristics, can significantly boost image quality. However, producing good negative prompts is manual and tedious. To address this, we propose NegOpt, a novel method for optimizing negative prompt generation toward enhanced image generation, using supervised fine-tuning and reinforcement learning. Our combined approach results in a substantial increase of 25% in Inception Score compared to other approaches and surpasses ground-truth negative prompts from the test set. Furthermore, with NegOpt we can preferentially optimize the metrics most important to us. Finally, we construct Negative Prompts DB (https://huggingface.co/datasets/mikeogezi/negopt_full), a publicly available dataset of negative prompts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07605 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimizing Negative Prompts for Enhanced Aesthetics and Fidelity in Text-To-Image Generation Ogezi, Michael Shi, Ning Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning In text-to-image generation, using negative prompts, which describe undesirable image characteristics, can significantly boost image quality. However, producing good negative prompts is manual and tedious. To address this, we propose NegOpt, a novel method for optimizing negative prompt generation toward enhanced image generation, using supervised fine-tuning and reinforcement learning. Our combined approach results in a substantial increase of 25% in Inception Score compared to other approaches and surpasses ground-truth negative prompts from the test set. Furthermore, with NegOpt we can preferentially optimize the metrics most important to us. Finally, we construct Negative Prompts DB (https://huggingface.co/datasets/mikeogezi/negopt_full), a publicly available dataset of negative prompts. |
| title | Optimizing Negative Prompts for Enhanced Aesthetics and Fidelity in Text-To-Image Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2403.07605 |