The Chosen One: Consistent Characters in Text-to-Image Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929419112677376 |
|---|---|
| author | Avrahami, Omri Hertz, Amir Vinker, Yael Arar, Moab Fruchter, Shlomi Fried, Ohad Cohen-Or, Daniel Lischinski, Dani |
| author_facet | Avrahami, Omri Hertz, Amir Vinker, Yael Arar, Moab Fruchter, Shlomi Fried, Ohad Cohen-Or, Daniel Lischinski, Dani |
| contents | Recent advances in text-to-image generation models have unlocked vast potential for visual creativity. However, the users that use these models struggle with the generation of consistent characters, a crucial aspect for numerous real-world applications such as story visualization, game development, asset design, advertising, and more. Current methods typically rely on multiple pre-existing images of the target character or involve labor-intensive manual processes. In this work, we propose a fully automated solution for consistent character generation, with the sole input being a text prompt. We introduce an iterative procedure that, at each stage, identifies a coherent set of images sharing a similar identity and extracts a more consistent identity from this set. Our quantitative analysis demonstrates that our method strikes a better balance between prompt alignment and identity consistency compared to the baseline methods, and these findings are reinforced by a user study. To conclude, we showcase several practical applications of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_10093 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | The Chosen One: Consistent Characters in Text-to-Image Diffusion Models Avrahami, Omri Hertz, Amir Vinker, Yael Arar, Moab Fruchter, Shlomi Fried, Ohad Cohen-Or, Daniel Lischinski, Dani Computer Vision and Pattern Recognition Graphics Machine Learning Recent advances in text-to-image generation models have unlocked vast potential for visual creativity. However, the users that use these models struggle with the generation of consistent characters, a crucial aspect for numerous real-world applications such as story visualization, game development, asset design, advertising, and more. Current methods typically rely on multiple pre-existing images of the target character or involve labor-intensive manual processes. In this work, we propose a fully automated solution for consistent character generation, with the sole input being a text prompt. We introduce an iterative procedure that, at each stage, identifies a coherent set of images sharing a similar identity and extracts a more consistent identity from this set. Our quantitative analysis demonstrates that our method strikes a better balance between prompt alignment and identity consistency compared to the baseline methods, and these findings are reinforced by a user study. To conclude, we showcase several practical applications of our approach. |
| title | The Chosen One: Consistent Characters in Text-to-Image Diffusion Models |
| topic | Computer Vision and Pattern Recognition Graphics Machine Learning |
| url | https://arxiv.org/abs/2311.10093 |