-
MCG-NJU/SteadyDancer-14B
Image-to-Video • Updated • 1.58k • 64 -
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation
Paper • 2511.19320 • Published • 42 -
MCG-NJU/X-Dance
Viewer • Updated • 36 • 1.23k • 17 -
MCG-NJU/SteadyDancer-GGUF
Image-to-Video • 16B • Updated • 18.8k • 18
AI & ML interests
Computer Vision; Video Understanding; Action Recognition
Recent Activity
View all activity
Papers
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation
SAM 2++: Tracking Anything at Any Granularity
-
MCG-NJU/SteadyDancer-14B
Image-to-Video • Updated • 1.58k • 64 -
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation
Paper • 2511.19320 • Published • 42 -
MCG-NJU/X-Dance
Viewer • Updated • 36 • 1.23k • 17 -
MCG-NJU/SteadyDancer-GGUF
Image-to-Video • 16B • Updated • 18.8k • 18
Learning Human Skill Generators at Key-Step Levels
CaReBench data, CaRe models and all the contrastively trained MLLMs (including InternVL2, MiniCPM-V 2.6, LLaVA NeXT Video, Qwen2-VL and Tariser).