Motion inversion for video customization

L Wang, Z Mai, G Shen, Y Liang, X Tao, P Wan… - arXiv preprint arXiv …, 2024 - arxiv.org
In this work, we present a novel approach for motion customization in video generation,
addressing the widespread gap in the exploration of motion representation within video …

Fastvideoedit: Leveraging consistency models for efficient text-to-video editing

Y Zhang, X Ju, JJ Clark - arXiv preprint arXiv:2403.06269, 2024 - arxiv.org
Diffusion models have demonstrated remarkable capabilities in text-to-image and text-to-
video generation, opening up possibilities for video editing based on textual input. However …

Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion

X Fan, A Bhattad, R Krishna - arXiv preprint arXiv:2403.14617, 2024 - arxiv.org
We introduce Videoshop, a training-free video editing algorithm for localized semantic edits.
Videoshop allows users to use any editing software, including Photoshop and generative …

Importance-based Token Merging for Diffusion Models

H Wu, J Xu, H Le, D Samaras - arXiv preprint arXiv:2411.16720, 2024 - arxiv.org
Diffusion models excel at high-quality image and video generation. However, a major
drawback is their high latency. A simple yet powerful way to speed them up is by merging …

UniVST: A Unified Framework for Training-free Localized Video Style Transfer

Q Song, M Lin, W Zhan, S Yan, L Cao - arXiv preprint arXiv:2410.20084, 2024 - arxiv.org
This paper presents UniVST, a unified framework for localized video style transfer. It
operates without the need for training, offering a distinct advantage over existing methods …

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration

W Sun, RC Tu, J Liao, Z Jin, D Tao - arXiv preprint arXiv:2412.11706, 2024 - arxiv.org
Video Diffusion Transformers (DiTs) have demonstrated significant potential for generating
high-fidelity videos but are computationally intensive. Existing acceleration methods include …

Mobile Video Diffusion

HB Yahia, D Korzhenkov, I Lelekas, A Ghodrati… - arXiv preprint arXiv …, 2024 - arxiv.org
Video diffusion models have achieved impressive realism and controllability but are limited
by high computational demands, restricting their use on mobile devices. This paper …

OmniCreator: Self-Supervised Unified Generation with Universal Editing

H Chen, L Wang, H Yang, SN Lim - arXiv preprint arXiv:2412.02114, 2024 - arxiv.org
We introduce OmniCreator, a novel framework that can conduct text-prompted unified
(image+ video) generation as well as editing all in one place. OmniCreator acquires …