Self-rectifying diffusion sampling with perturbed-attention guidance

D Ahn, H Cho, J Min, W Jang, J Kim, SH Kim… - … on Computer Vision, 2025 - Springer
Recent studies have demonstrated that diffusion models can generate high-quality samples,
but their quality heavily depends on sampling guidance techniques, such as classifier …

Swapanything: Enabling arbitrary object swapping in personalized visual editing

J Gu, N Zhao, W Xiong, Q Liu, Z Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Effective editing of personal content holds a pivotal role in enabling individuals to express
their creativity, weaving captivating narratives within their visual stories, and elevate the …

SwapAnything: Enabling arbitrary object swapping in personalized image editing

J Gu, N Zhao, W Xiong, Q Liu, Z Zhang… - … on Computer Vision, 2025 - Springer
Effective editing of personal content holds a pivotal role in enabling individuals to express
their creativity, weaving captivating narratives within their visual stories, and elevate the …

Addressing Attribute Leakages in Diffusion-based Image Editing without Training

S Mun, J Nam, S Cho, J Ok - arXiv preprint arXiv:2412.04715, 2024 - arxiv.org
Diffusion models have become a cornerstone in image editing, offering flexibility with
language prompts and source images. However, a key challenge is attribute leakage, where …

CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing

X Xian, X He, Z Niu, J Zhang, W Xie, S Song… - arXiv preprint arXiv …, 2024 - arxiv.org
For efficient and high-fidelity local facial attribute editing, most existing editing methods
either require additional fine-tuning for different editing effects or tend to affect beyond the …