Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis
Paper
•
2509.09595
•
Published
•
48
HU Wentao
VincentHu
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Kling-Avatar: Grounding Multimodal Instructions for Cascaded
Long-Duration Avatar Animation Synthesis
upvoted
a
paper
about 2 months ago
MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time
Autoregressive Video Generation
Organizations
upvoted
a
paper
about 1 month ago