Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis
Paper
•
2509.09595
•
Published
•
48
liuxiaoqiang
liuxq
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time
Autoregressive Video Generation
liked
a model
over 1 year ago
stabilityai/stable-diffusion-3-medium
Organizations
None yet
