FlexIP: Dynamic Control of Preservation and Personality for Customized Image Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916683023646720 |
|---|---|
| author | Huang, Linyan Lin, Haonan Zhou, Yanning Xiao, Kaiwen |
| author_facet | Huang, Linyan Lin, Haonan Zhou, Yanning Xiao, Kaiwen |
| contents | With the rapid advancement of 2D generative models, preserving subject identity while enabling diverse editing has emerged as a critical research focus. Existing methods typically face inherent trade-offs between identity preservation and personalized manipulation. We introduce FlexIP, a novel framework that decouples these objectives through two dedicated components: a Personalization Adapter for stylistic manipulation and a Preservation Adapter for identity maintenance. By explicitly injecting both control mechanisms into the generative model, our framework enables flexible parameterized control during inference through dynamic tuning of the weight adapter. Experimental results demonstrate that our approach breaks through the performance limitations of conventional methods, achieving superior identity preservation while supporting more diverse personalized generation capabilities (Project Page: https://flexip-tech.github.io/flexip/). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07405 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FlexIP: Dynamic Control of Preservation and Personality for Customized Image Generation Huang, Linyan Lin, Haonan Zhou, Yanning Xiao, Kaiwen Computer Vision and Pattern Recognition With the rapid advancement of 2D generative models, preserving subject identity while enabling diverse editing has emerged as a critical research focus. Existing methods typically face inherent trade-offs between identity preservation and personalized manipulation. We introduce FlexIP, a novel framework that decouples these objectives through two dedicated components: a Personalization Adapter for stylistic manipulation and a Preservation Adapter for identity maintenance. By explicitly injecting both control mechanisms into the generative model, our framework enables flexible parameterized control during inference through dynamic tuning of the weight adapter. Experimental results demonstrate that our approach breaks through the performance limitations of conventional methods, achieving superior identity preservation while supporting more diverse personalized generation capabilities (Project Page: https://flexip-tech.github.io/flexip/). |
| title | FlexIP: Dynamic Control of Preservation and Personality for Customized Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.07405 |