Abstract: In the scenario of text data and image data interact of the Internet of Things (IoT) applications, the problem of copyright protection of the text-to-image models is threatened due to the ...

We present Diffusion-4K, a novel framework for direct ultra-high-resolution image synthesis using text-to-image diffusion models. The core advancements include: (1) Aesthetic-4K Benchmark: addressing ...

Jun 5, 2025: We released our script and Blender project for creating synthetic datasets. Jun 2, 2025: We added inference code based on Wan2.1Fun 1.3B fine-tuning to the Wanfun branch. Apr 2, 2025: ...

Abstract: To achieve a balance between visual privacy protection and visual information integrity, we propose a visual privacy protection method based on YOLOv8 and ControlNet. In the privacy ...

There is a persistent belief in modern political life that systems fail because they become fragile. Institutions, it is assumed, weaken under pressure and eventually break down. This intuition is not ...