DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation
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_ | 1866915250287149056 |
|---|---|
| author | Zhao, Brian Nlong Xiao, Yuhang Xu, Jiashu Jiang, Xinyang Yang, Yifan Li, Dongsheng Itti, Laurent Vineet, Vibhav Ge, Yunhao |
| author_facet | Zhao, Brian Nlong Xiao, Yuhang Xu, Jiashu Jiang, Xinyang Yang, Yifan Li, Dongsheng Itti, Laurent Vineet, Vibhav Ge, Yunhao |
| contents | The popularization of Text-to-Image (T2I) diffusion models enables the generation of high-quality images from text descriptions. However, generating diverse customized images with reference visual attributes remains challenging. This work focuses on personalizing T2I diffusion models at a more abstract concept or category level, adapting commonalities from a set of reference images while creating new instances with sufficient variations. We introduce a solution that allows a pretrained T2I diffusion model to learn a set of soft prompts, enabling the generation of novel images by sampling prompts from the learned distribution. These prompts offer text-guided editing capabilities and additional flexibility in controlling variation and mixing between multiple distributions. We also show the adaptability of the learned prompt distribution to other tasks, such as text-to-3D. Finally we demonstrate effectiveness of our approach through quantitative analysis including automatic evaluation and human assessment. Project website: https://briannlongzhao.github.io/DreamDistribution |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_14216 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation Zhao, Brian Nlong Xiao, Yuhang Xu, Jiashu Jiang, Xinyang Yang, Yifan Li, Dongsheng Itti, Laurent Vineet, Vibhav Ge, Yunhao Computer Vision and Pattern Recognition The popularization of Text-to-Image (T2I) diffusion models enables the generation of high-quality images from text descriptions. However, generating diverse customized images with reference visual attributes remains challenging. This work focuses on personalizing T2I diffusion models at a more abstract concept or category level, adapting commonalities from a set of reference images while creating new instances with sufficient variations. We introduce a solution that allows a pretrained T2I diffusion model to learn a set of soft prompts, enabling the generation of novel images by sampling prompts from the learned distribution. These prompts offer text-guided editing capabilities and additional flexibility in controlling variation and mixing between multiple distributions. We also show the adaptability of the learned prompt distribution to other tasks, such as text-to-3D. Finally we demonstrate effectiveness of our approach through quantitative analysis including automatic evaluation and human assessment. Project website: https://briannlongzhao.github.io/DreamDistribution |
| title | DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.14216 |