Self-rectifying diffusion sampling with perturbed-attention guidance
Recent studies have demonstrated that diffusion models can generate high-quality samples,
but their quality heavily depends on sampling guidance techniques, such as classifier …
but their quality heavily depends on sampling guidance techniques, such as classifier …
Swapanything: Enabling arbitrary object swapping in personalized visual editing
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 …
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 …
their creativity, weaving captivating narratives within their visual stories, and elevate the …
Addressing Attribute Leakages in Diffusion-based Image Editing without Training
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 …
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
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 …
either require additional fine-tuning for different editing effects or tend to affect beyond the …