Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Lin, Shanchuan"'
Autor:
Yu, Weichen, Yang, Ziyan, Lin, Shanchuan, Zhao, Qi, Wang, Jianyi, Gui, Liangke, Fredrikson, Matt, Jiang, Lu
In text-to-image (T2I) generation, a prevalent training technique involves utilizing Vision Language Models (VLMs) for image re-captioning. Even though VLMs are known to exhibit hallucination, generating descriptive content that deviates from the vis
Externí odkaz:
http://arxiv.org/abs/2412.19531
Autor:
Lin, Shanchuan, Yang, Xiao
We present AnimateDiff-Lightning for lightning-fast video generation. Our model uses progressive adversarial diffusion distillation to achieve new state-of-the-art in few-step video generation. We discuss our modifications to adapt it for the video m
Externí odkaz:
http://arxiv.org/abs/2403.12706
We propose a diffusion distillation method that achieves new state-of-the-art in one-step/few-step 1024px text-to-image generation based on SDXL. Our method combines progressive and adversarial distillation to achieve a balance between quality and mo
Externí odkaz:
http://arxiv.org/abs/2402.13929
Autor:
Lin, Shanchuan, Yang, Xiao
Diffusion models without guidance tend to generate unrealistic samples, yet the cause of this problem is not fully studied. Our analysis suggests that the loss objective plays an important role in shaping the learned distribution and the common mean
Externí odkaz:
http://arxiv.org/abs/2401.00110
This paper addresses the issue of modifying the visual appearance of videos while preserving their motion. A novel framework, named MagicProp, is proposed, which disentangles the video editing process into two stages: appearance editing and motion-aw
Externí odkaz:
http://arxiv.org/abs/2309.00908
We discover that common diffusion noise schedules do not enforce the last timestep to have zero signal-to-noise ratio (SNR), and some implementations of diffusion samplers do not start from the last timestep. Such designs are flawed and do not reflec
Externí odkaz:
http://arxiv.org/abs/2305.08891
We introduce a robust, real-time, high-resolution human video matting method that achieves new state-of-the-art performance. Our method is much lighter than previous approaches and can process 4K at 76 FPS and HD at 104 FPS on an Nvidia GTX 1080Ti GP
Externí odkaz:
http://arxiv.org/abs/2108.11515
Autor:
Lin, Shanchuan, Ryabtsev, Andrey, Sengupta, Soumyadip, Curless, Brian, Seitz, Steve, Kemelmacher-Shlizerman, Ira
We introduce a real-time, high-resolution background replacement technique which operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU. Our technique is based on background matting, where an additional frame of the background is captur
Externí odkaz:
http://arxiv.org/abs/2012.07810
Autor:
Wadden, David, Lin, Shanchuan, Lo, Kyle, Wang, Lucy Lu, van Zuylen, Madeleine, Cohan, Arman, Hajishirzi, Hannaneh
We introduce scientific claim verification, a new task to select abstracts from the research literature containing evidence that SUPPORTS or REFUTES a given scientific claim, and to identify rationales justifying each decision. To study this task, we
Externí odkaz:
http://arxiv.org/abs/2004.14974
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.