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
Task
Prompt
Frame Interpolation
Frame Interpolation
Video Resolution
Video Resolution
Aspect Ratio
Aspect Ratio
Video Duration (seconds)
Video Duration (seconds)
Output Resolution
Seed (-1 for random seed)
Validation Num Timesteps
1 50
Validation Timestep Shift
CFG Text Scale
Output Video
Run Logs
Video edit recommended cases
Prompt / Instruction / Question
Input Video
0:00 / 0:00
0:00 / 0:00
0:00 / 0:00
Video understanding recommended cases
Prompt / Instruction / Question
Input Video
0:00 / 0:00
0:00 / 0:00
0:00 / 0:00
Image generation recommended cases
Prompt
Image edit recommended cases
Prompt / Instruction / Question
Input Image
Image understanding recommended cases
Prompt / Instruction / Question
Input Image