34 citations · 104 across the 31 of their papers we have counts for
10 papers · 1 filter
FreeInit: Bridging Initialization Gap in Video Diffusion Models
Tianxing Wu, Chenyang Si, Yuming Jiang +2
Though diffusion-based video generation has witnessed rapid progress, the inference results of existing models still exhibit unsatisfactory temporal consistency and unnatural dynam…
VideoBooth: Diffusion-based Video Generation with Image Prompts
Yuming Jiang, Tianxing Wu, Shuai Yang +5
Text-driven video generation witnesses rapid progress. However, merely using text prompts is not enough to depict the desired subject appearance that accurately aligns with users'…
VBench: Comprehensive Benchmark Suite for Video Generative Models
Ziqi Huang, Yinan He, Jiashuo Yu +13
Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable…
FreeU: Free Lunch in Diffusion U-Net
Chenyang Si, Ziqi Huang, Yuming Jiang +1
In this paper, we uncover the untapped potential of diffusion U-Net, which serves as a "free lunch" that substantially improves the generation quality on the fly. We initially inve…
LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models
Yaohui Wang, Xinyuan Chen, Xin Ma +17
This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challengi…
UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation
Jianglin Fu, Shikai Li, Yuming Jiang +3
Human generation has achieved significant progress. Nonetheless, existing methods still struggle to synthesize specific regions such as faces and hands. We argue that the main reas…
ReliTalk: Relightable Talking Portrait Generation from a Single Video
Haonan Qiu, Zhaoxi Chen, Yuming Jiang +5
Recent years have witnessed great progress in creating vivid audio-driven portraits from monocular videos. However, how to seamlessly adapt the created video avatars to other scena…
Collaborative Diffusion for Multi-Modal Face Generation and Editing
Ziqi Huang, Kelvin C. K. Chan, Yuming Jiang +1
Diffusion models arise as a powerful generative tool recently. Despite the great progress, existing diffusion models mainly focus on uni-modal control, i.e., the diffusion process…
Text2Performer: Text-Driven Human Video Generation
Yuming Jiang, Shuai Yang, Tong Liang Koh +3
Text-driven content creation has evolved to be a transformative technique that revolutionizes creativity. Here we study the task of text-driven human video generation, where a vide…
ReVersion: Diffusion-Based Relation Inversion from Images
Ziqi Huang, Tianxing Wu, Yuming Jiang +2
Diffusion models gain increasing popularity for their generative capabilities. Recently, there have been surging needs to generate customized images by inverting diffusion models f…