An Improved Method for Personalizing Diffusion Models
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_ | 1866907971367206912 |
|---|---|
| author | Zeng, Yan Suganuma, Masanori Okatani, Takayuki |
| author_facet | Zeng, Yan Suganuma, Masanori Okatani, Takayuki |
| contents | Diffusion models have demonstrated impressive image generation capabilities. Personalized approaches, such as textual inversion and Dreambooth, enhance model individualization using specific images. These methods enable generating images of specific objects based on diverse textual contexts. Our proposed approach aims to retain the model's original knowledge during new information integration, resulting in superior outcomes while necessitating less training time compared to Dreambooth and textual inversion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_05312 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Improved Method for Personalizing Diffusion Models Zeng, Yan Suganuma, Masanori Okatani, Takayuki Computer Vision and Pattern Recognition Diffusion models have demonstrated impressive image generation capabilities. Personalized approaches, such as textual inversion and Dreambooth, enhance model individualization using specific images. These methods enable generating images of specific objects based on diverse textual contexts. Our proposed approach aims to retain the model's original knowledge during new information integration, resulting in superior outcomes while necessitating less training time compared to Dreambooth and textual inversion. |
| title | An Improved Method for Personalizing Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.05312 |