paper-with-me

홈 › Papers

Beyond Sliders: Mastering the Art of Diffusion-based Image Manipulation

2025-09-14 · Yufei Tang, Daiheng Gao, Pingyu Wu, Wenbo Zhou, Bang Zhang, Weiming Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.11213

Code (0)

등록된 구현이 없습니다.

Tasks

Image ManipulationImage Generation

Similar Papers 제목 키워드 기반

Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models

2023-11-20 · Rohit Gandikota, Joanna Materzynska, Tingrui Zhou, Antonio Torralba 외

We present a method to create interpretable concept sliders that enable precise control over attributes in image generations from diffusion models. Our approach identifies a low-rank parameter direction corresponding to …

Image Generation

TexSliders: Diffusion-Based Texture Editing in CLIP Space

2024-05-01 · Julia Guerrero-Viu, Milos Hasan, Arthur Roullier, Midhun Harikumar 외

Generative models have enabled intuitive image creation and manipulation using natural language. In particular, diffusion models have recently shown remarkable results for natural image editing. In this work, we propose …

Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Models

2024-09-25 · Deepak Sridhar, Nuno Vasconcelos

Diffusion models have recently surpassed GANs in image synthesis and editing, offering superior image quality and diversity. However, achieving precise control over attributes in generated images remains a challenge. Con…

Image Generation

SliderSpace: Decomposing the Visual Capabilities of Diffusion Models

2025-02-03 · Rohit Gandikota, Zongze Wu, Richard Zhang, David Bau 외

We present SliderSpace, a framework for automatically decomposing the visual capabilities of diffusion models into controllable and human-understandable directions. Unlike existing control methods that require a user to …

Diversity

FreeSliders: Training-Free, Modality-Agnostic Concept Sliders for Fine-Grained Diffusion Control in Images, Audio, and Video

2025-10-30 · Rotem Ezra, Hedi Zisling, Nimrod Berman, Ilan Naiman 외 arxiv

Diffusion models have become state-of-the-art generative models for images, audio, and video, yet enabling fine-grained controllable generation, i.e., continuously steering specific concepts without disturbing unrelated …