Beyond Sliders: Mastering the Art of Diffusion-based Image Manipulation
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_ | 1866915494152372224 |
|---|---|
| author | Tang, Yufei Gao, Daiheng Wu, Pingyu Zhou, Wenbo Zhang, Bang Zhang, Weiming |
| author_facet | Tang, Yufei Gao, Daiheng Wu, Pingyu Zhou, Wenbo Zhang, Bang Zhang, Weiming |
| contents | In the realm of image generation, the quest for realism and customization has never been more pressing. While existing methods like concept sliders have made strides, they often falter when it comes to no-AIGC images, particularly images captured in real world settings. To bridge this gap, we introduce Beyond Sliders, an innovative framework that integrates GANs and diffusion models to facilitate sophisticated image manipulation across diverse image categories. Improved upon concept sliders, our method refines the image through fine grained guidance both textual and visual in an adversarial manner, leading to a marked enhancement in image quality and realism. Extensive experimental validation confirms the robustness and versatility of Beyond Sliders across a spectrum of applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11213 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Sliders: Mastering the Art of Diffusion-based Image Manipulation Tang, Yufei Gao, Daiheng Wu, Pingyu Zhou, Wenbo Zhang, Bang Zhang, Weiming Computer Vision and Pattern Recognition In the realm of image generation, the quest for realism and customization has never been more pressing. While existing methods like concept sliders have made strides, they often falter when it comes to no-AIGC images, particularly images captured in real world settings. To bridge this gap, we introduce Beyond Sliders, an innovative framework that integrates GANs and diffusion models to facilitate sophisticated image manipulation across diverse image categories. Improved upon concept sliders, our method refines the image through fine grained guidance both textual and visual in an adversarial manner, leading to a marked enhancement in image quality and realism. Extensive experimental validation confirms the robustness and versatility of Beyond Sliders across a spectrum of applications. |
| title | Beyond Sliders: Mastering the Art of Diffusion-based Image Manipulation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.11213 |