StyleBooth: Image Style Editing with Multimodal Instruction
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_ | 1866909429196128256 |
|---|---|
| author | Han, Zhen Mao, Chaojie Jiang, Zeyinzi Pan, Yulin Zhang, Jingfeng |
| author_facet | Han, Zhen Mao, Chaojie Jiang, Zeyinzi Pan, Yulin Zhang, Jingfeng |
| contents | Given an original image, image editing aims to generate an image that align with the provided instruction. The challenges are to accept multimodal inputs as instructions and a scarcity of high-quality training data, including crucial triplets of source/target image pairs and multimodal (text and image) instructions. In this paper, we focus on image style editing and present StyleBooth, a method that proposes a comprehensive framework for image editing and a feasible strategy for building a high-quality style editing dataset. We integrate encoded textual instruction and image exemplar as a unified condition for diffusion model, enabling the editing of original image following multimodal instructions. Furthermore, by iterative style-destyle tuning and editing and usability filtering, the StyleBooth dataset provides content-consistent stylized/plain image pairs in various categories of styles. To show the flexibility of StyleBooth, we conduct experiments on diverse tasks, such as text-based style editing, exemplar-based style editing and compositional style editing. The results demonstrate that the quality and variety of training data significantly enhance the ability to preserve content and improve the overall quality of generated images in editing tasks. Project page can be found at https://ali-vilab.github.io/stylebooth-page/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_12154 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | StyleBooth: Image Style Editing with Multimodal Instruction Han, Zhen Mao, Chaojie Jiang, Zeyinzi Pan, Yulin Zhang, Jingfeng Computer Vision and Pattern Recognition Given an original image, image editing aims to generate an image that align with the provided instruction. The challenges are to accept multimodal inputs as instructions and a scarcity of high-quality training data, including crucial triplets of source/target image pairs and multimodal (text and image) instructions. In this paper, we focus on image style editing and present StyleBooth, a method that proposes a comprehensive framework for image editing and a feasible strategy for building a high-quality style editing dataset. We integrate encoded textual instruction and image exemplar as a unified condition for diffusion model, enabling the editing of original image following multimodal instructions. Furthermore, by iterative style-destyle tuning and editing and usability filtering, the StyleBooth dataset provides content-consistent stylized/plain image pairs in various categories of styles. To show the flexibility of StyleBooth, we conduct experiments on diverse tasks, such as text-based style editing, exemplar-based style editing and compositional style editing. The results demonstrate that the quality and variety of training data significantly enhance the ability to preserve content and improve the overall quality of generated images in editing tasks. Project page can be found at https://ali-vilab.github.io/stylebooth-page/. |
| title | StyleBooth: Image Style Editing with Multimodal Instruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.12154 |