Lance: Unified Multimodal Modeling by Multi-Task Synergy

Fengyi Fu*, Mengqi Huang*,✉, Shaojin Wu*, Yunsheng Jiang*, Yufei Huo, Jianzhu Guo✉,§
Hao Li, Yinghang Song, Fei Ding, Qian He, Zheren Fu, Zhendong Mao, Yongdong Zhang
ByteDance
Homepage Paper Hugging Face GitHub
Task
Prompt
Motion Smoothing
Video Resolution
Aspect Ratio
Video Duration
1 50
Output Video
Video edit recommended cases
Video understanding recommended cases
Image generation recommended cases
Image edit recommended cases
edit_img.jpg
edit_img.jpg
edit_img.jpg
edit_img.jpg
edit_img.jpg
Image understanding recommended cases
image-understanding-case-05.png
image-understanding-case-06.png
image-understanding-case-02.png