Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.08116 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916649527934976 |
|---|---|
| author | Wang, Ruipeng Fang, Junfeng Li, Jiaqi Chen, Hao Shi, Jie Wang, Kun Wang, Xiang |
| author_facet | Wang, Ruipeng Fang, Junfeng Li, Jiaqi Chen, Hao Shi, Jie Wang, Kun Wang, Xiang |
| contents | Diffusion-based text-to-image models have demonstrated remarkable capabilities in generating realistic images, but they raise societal and ethical concerns, such as the creation of unsafe content. While concept editing is proposed to address these issues, they often struggle to balance the removal of unsafe concept with maintaining the model's general genera-tive capabilities. In this work, we propose ACE, a new editing method that enhances concept editing in diffusion models. ACE introduces a novel cross null-space projection approach to precisely erase unsafe concept while maintaining the model's ability to generate high-quality, semantically consistent images. Extensive experiments demonstrate that ACE significantly outperforms the advancing baselines,improving semantic consistency by 24.56% and image generation quality by 34.82% on average with only 1% of the time cost. These results highlight the practical utility of concept editing by mitigating its potential risks, paving the way for broader applications in the field. Code is avaliable at https://github.com/littlelittlenine/ACE-zero.git |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08116 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ACE: Concept Editing in Diffusion Models without Performance Degradation Wang, Ruipeng Fang, Junfeng Li, Jiaqi Chen, Hao Shi, Jie Wang, Kun Wang, Xiang Computer Vision and Pattern Recognition Diffusion-based text-to-image models have demonstrated remarkable capabilities in generating realistic images, but they raise societal and ethical concerns, such as the creation of unsafe content. While concept editing is proposed to address these issues, they often struggle to balance the removal of unsafe concept with maintaining the model's general genera-tive capabilities. In this work, we propose ACE, a new editing method that enhances concept editing in diffusion models. ACE introduces a novel cross null-space projection approach to precisely erase unsafe concept while maintaining the model's ability to generate high-quality, semantically consistent images. Extensive experiments demonstrate that ACE significantly outperforms the advancing baselines,improving semantic consistency by 24.56% and image generation quality by 34.82% on average with only 1% of the time cost. These results highlight the practical utility of concept editing by mitigating its potential risks, paving the way for broader applications in the field. Code is avaliable at https://github.com/littlelittlenine/ACE-zero.git |
| title | ACE: Concept Editing in Diffusion Models without Performance Degradation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.08116 |