Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Zhan, Wengyi"'
We introduce DiffusionTrend for virtual fashion try-on, which forgoes the need for retraining diffusion models. Using advanced diffusion models, DiffusionTrend harnesses latent information rich in prior information to capture the nuances of garment d
Externí odkaz:
http://arxiv.org/abs/2412.14465
Diffusion models suffer severe object repetition and local distortion when the inference resolution differs from its pre-trained resolution. We propose AccDiffusion v2, an accurate method for patch-wise higher-resolution diffusion extrapolation witho
Externí odkaz:
http://arxiv.org/abs/2412.02099
This paper presents UniVST, a unified framework for localized video style transfer based on diffusion model. It operates without the need for training, offering a distinct advantage over existing diffusion methods that transfer style across entire vi
Externí odkaz:
http://arxiv.org/abs/2410.20084
In an effort to improve the efficiency and scalability of single-image super-resolution (SISR) applications, we introduce AnySR, to rebuild existing arbitrary-scale SR methods into any-scale, any-resource implementation. As a contrast to off-the-shel
Externí odkaz:
http://arxiv.org/abs/2407.04241
Transforming large pre-trained low-resolution diffusion models to cater to higher-resolution demands, i.e., diffusion extrapolation, significantly improves diffusion adaptability. We propose tuning-free CutDiffusion, aimed at simplifying and accelera
Externí odkaz:
http://arxiv.org/abs/2404.15141