BRAT: Bonus oRthogonAl Token for Architecture Agnostic Textual Inversion
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929453903380480 |
|---|---|
| author | Baker, James |
| author_facet | Baker, James |
| contents | Textual Inversion remains a popular method for personalizing diffusion models, in order to teach models new subjects and styles. We note that textual inversion has been underexplored using alternatives to the UNet, and experiment with textual inversion with a vision transformer. We also seek to optimize textual inversion using a strategy that does not require explicit use of the UNet and its idiosyncratic layers, so we add bonus tokens and enforce orthogonality. We find the use of the bonus token improves adherence to the source images and the use of the vision transformer improves adherence to the prompt. Code is available at https://github.com/jamesBaker361/tex_inv_plus. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04785 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BRAT: Bonus oRthogonAl Token for Architecture Agnostic Textual Inversion Baker, James Computer Vision and Pattern Recognition Textual Inversion remains a popular method for personalizing diffusion models, in order to teach models new subjects and styles. We note that textual inversion has been underexplored using alternatives to the UNet, and experiment with textual inversion with a vision transformer. We also seek to optimize textual inversion using a strategy that does not require explicit use of the UNet and its idiosyncratic layers, so we add bonus tokens and enforce orthogonality. We find the use of the bonus token improves adherence to the source images and the use of the vision transformer improves adherence to the prompt. Code is available at https://github.com/jamesBaker361/tex_inv_plus. |
| title | BRAT: Bonus oRthogonAl Token for Architecture Agnostic Textual Inversion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.04785 |