7 papers
Universal Adversarial Purification with DDIM Metric Loss for Stable Diffusion
Li Zheng, Liangbin Xie, Jiantao Zhou +1
Stable Diffusion (SD) often produces degraded outputs when the training dataset contains adversarial noise. Adversarial purification offers a promising solution by removing adversa…
SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution
Liangbin Xie, Yu Li, Shian Du +7
Latent diffusion models have emerged as a leading paradigm for efficient video generation. However, as user expectations shift toward higher-resolution outputs, relying solely on l…
VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
Yuxuan Bian, Zhaoyang Zhang, Xuan Ju +4
Video inpainting, which aims to restore corrupted video content, has experienced substantial progress. Despite these advances, existing methods, whether propagating unmasked region…
Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision
Yuandong Pu, Le Zhuo, Kaiwen Zhu +7
We present Lunima-OmniLV (abbreviated as OmniLV), a universal multimodal multi-task framework for low-level vision that addresses over 100 sub-tasks across four major categories: i…
TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting
Liangbin Xie, Daniil Pakhomov, Zhonghao Wang +8
This paper introduces TurboFill, a fast image inpainting model that enhances a few-step text-to-image diffusion model with an inpainting adapter for high-quality and efficient inpa…
Anti-Diffusion: Preventing Abuse of Modifications of Diffusion-Based Models
Zheng Li, Liangbin Xie, Jiantao Zhou +3
Although diffusion-based techniques have shown remarkable success in image generation and editing tasks, their abuse can lead to severe negative social impacts. Recently, some work…