AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
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_ | 1866916665487261696 |
|---|---|
| author | Yu, Qifan Chow, Wei Yue, Zhongqi Pan, Kaihang Wu, Yang Wan, Xiaoyang Li, Juncheng Tang, Siliang Zhang, Hanwang Zhuang, Yueting |
| author_facet | Yu, Qifan Chow, Wei Yue, Zhongqi Pan, Kaihang Wu, Yang Wan, Xiaoyang Li, Juncheng Tang, Siliang Zhang, Hanwang Zhuang, Yueting |
| contents | Instruction-based image editing aims to modify specific image elements with natural language instructions. However, current models in this domain often struggle to accurately execute complex user instructions, as they are trained on low-quality data with limited editing types. We present AnyEdit, a comprehensive multi-modal instruction editing dataset, comprising 2.5 million high-quality editing pairs spanning over 20 editing types and five domains. We ensure the diversity and quality of the AnyEdit collection through three aspects: initial data diversity, adaptive editing process, and automated selection of editing results. Using the dataset, we further train a novel AnyEdit Stable Diffusion with task-aware routing and learnable task embedding for unified image editing. Comprehensive experiments on three benchmark datasets show that AnyEdit consistently boosts the performance of diffusion-based editing models. This presents prospects for developing instruction-driven image editing models that support human creativity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15738 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea Yu, Qifan Chow, Wei Yue, Zhongqi Pan, Kaihang Wu, Yang Wan, Xiaoyang Li, Juncheng Tang, Siliang Zhang, Hanwang Zhuang, Yueting Computer Vision and Pattern Recognition Instruction-based image editing aims to modify specific image elements with natural language instructions. However, current models in this domain often struggle to accurately execute complex user instructions, as they are trained on low-quality data with limited editing types. We present AnyEdit, a comprehensive multi-modal instruction editing dataset, comprising 2.5 million high-quality editing pairs spanning over 20 editing types and five domains. We ensure the diversity and quality of the AnyEdit collection through three aspects: initial data diversity, adaptive editing process, and automated selection of editing results. Using the dataset, we further train a novel AnyEdit Stable Diffusion with task-aware routing and learnable task embedding for unified image editing. Comprehensive experiments on three benchmark datasets show that AnyEdit consistently boosts the performance of diffusion-based editing models. This presents prospects for developing instruction-driven image editing models that support human creativity. |
| title | AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.15738 |